Artificial+Intelligence
-
Energy-Efficient AI Hardware Technology Via a Brain-Inspired Stashing System
Researchers demonstrate neuromodulation-inspired stashing system for the energy-efficient learning of a spiking neural network using a self-rectifying memristor array
Researchers have proposed a novel system inspired by the neuromodulation of the brain, referred to as a ‘stashing system,’ that requires less energy consumption. The research group led by Professor Kyung Min Kim from the Department of Materials Science and Engineering has developed a technology that can efficiently handle mathematical operations for artificial intelligence by imitating the continuous changes in the topology of the neural network according to the situation. The human brain changes its neural topology in real time, learning to store or recall memories as needed. The research group presented a new artificial intelligence learning method that directly implements these neural coordination circuit configurations.
Research on artificial intelligence is becoming very active, and the development of artificial intelligence-based electronic devices and product releases are accelerating, especially in the Fourth Industrial Revolution age. To implement artificial intelligence in electronic devices, customized hardware development should also be supported. However most electronic devices for artificial intelligence require high power consumption and highly integrated memory arrays for large-scale tasks. It has been challenging to solve these power consumption and integration limitations, and efforts have been made to find out how the human brain solves problems.
To prove the efficiency of the developed technology, the research group created artificial neural network hardware equipped with a self-rectifying synaptic array and algorithm called a ‘stashing system’ that was developed to conduct artificial intelligence learning. As a result, it was able to reduce energy by 37% within the stashing system without any accuracy degradation. This result proves that emulating the neuromodulation in humans is possible.
Professor Kim said, "In this study, we implemented the learning method of the human brain with only a simple circuit composition and through this we were able to reduce the energy needed by nearly 40 percent.”
This neuromodulation-inspired stashing system that mimics the brain’s neural activity is compatible with existing electronic devices and commercialized semiconductor hardware. It is expected to be used in the design of next-generation semiconductor chips for artificial intelligence.
This study was published in Advanced Functional Materials in March 2022 and supported by KAIST, the National Research Foundation of Korea, the National NanoFab Center, and SK Hynix.
-Publication:
Woon Hyung Cheong, Jae Bum Jeon†, Jae Hyun In, Geunyoung Kim, Hanchan Song, Janho An, Juseong Park, Young Seok Kim, Cheol Seong Hwang, and Kyung Min Kim (2022)
“Demonstration of Neuromodulation-inspired Stashing System for Energy-efficient Learning of Spiking Neural Network using a Self-Rectifying Memristor Array,” Advanced FunctionalMaterials March 31, 2022 (DOI: 10.1002/adfm.202200337)
-Profile:
Professor Kyung Min Kimhttp://semi.kaist.ac.kr https://scholar.google.com/citations?user=BGw8yDYAAAAJ&hl=ko
Department of Materials Science and EngineeringKAIST
2022.05.18 View 12342 -
Machine Learning-Based Algorithm to Speed up DNA Sequencing
The algorithm presents the first full-fledged, short-read alignment software that leverages learned indices for solving the exact match search problem for efficient seeding
The human genome consists of a complete set of DNA, which is about 6.4 billion letters long. Because of its size, reading the whole genome sequence at once is challenging. So scientists use DNA sequencers to produce hundreds of millions of DNA sequence fragments, or short reads, up to 300 letters long. Then the DNA sequencer assembles all the short reads like a giant jigsaw puzzle to reconstruct the entire genome sequence. Even with very fast computers, this job can take hours to complete.
A research team at KAIST has achieved up to 3.45x faster speeds by developing the first short-read alignment software that uses a recent advance in machine-learning called a learned index.
The research team reported their findings on March 7, 2022 in the journal Bioinformatics. The software has been released as open source and can be found on github (https://github.com/kaist-ina/BWA-MEME).
Next-generation sequencing (NGS) is a state-of-the-art DNA sequencing method. Projects are underway with the goal of producing genome sequencing at population scale. Modern NGS hardware is capable of generating billions of short reads in a single run. Then the short reads have to be aligned with the reference DNA sequence. With large-scale DNA sequencing operations running hundreds of next-generation sequences, the need for an efficient short read alignment tool has become even more critical. Accelerating the DNA sequence alignment would be a step toward achieving the goal of population-scale sequencing. However, existing algorithms are limited in their performance because of their frequent memory accesses.
BWA-MEM2 is a popular short-read alignment software package currently used to sequence the DNA. However, it has its limitations. The state-of-the-art alignment has two phases – seeding and extending. During the seeding phase, searches find exact matches of short reads in the reference DNA sequence. During the extending phase, the short reads from the seeding phase are extended. In the current process, bottlenecks occur in the seeding phase. Finding the exact matches slows the process.
The researchers set out to solve the problem of accelerating the DNA sequence alignment. To speed the process, they applied machine learning techniques to create an algorithmic improvement. Their algorithm, BWA-MEME (BWA-MEM emulated) leverages learned indices to solve the exact match search problem. The original software compared one character at a time for an exact match search. The team’s new algorithm achieves up to 3.45x faster speeds in seeding throughput over BWA-MEM2 by reducing the number of instructions by 4.60x and memory accesses by 8.77x. “Through this study, it has been shown that full genome big data analysis can be performed faster and less costly than conventional methods by applying machine learning technology,” said Professor Dongsu Han from the School of Electrical Engineering at KAIST.
The researchers’ ultimate goal was to develop efficient software that scientists from academia and industry could use on a daily basis for analyzing big data in genomics. “With the recent advances in artificial intelligence and machine learning, we see so many opportunities for designing better software for genomic data analysis. The potential is there for accelerating existing analysis as well as enabling new types of analysis, and our goal is to develop such software,” added Han.
Whole genome sequencing has traditionally been used for discovering genomic mutations and identifying the root causes of diseases, which leads to the discovery and development of new drugs and cures. There could be many potential applications. Whole genome sequencing is used not only for research, but also for clinical purposes. “The science and technology for analyzing genomic data is making rapid progress to make it more accessible for scientists and patients. This will enhance our understanding about diseases and develop a better cure for patients of various diseases.”
The research was funded by the National Research Foundation of the Korean government’s Ministry of Science and ICT.
-PublicationYoungmok Jung, Dongsu Han, “BWA-MEME:BWA-MEM emulated with a machine learning approach,” Bioinformatics, Volume 38, Issue 9, May 2022
(https://doi.org/10.1093/bioinformatics/btac137)
-ProfileProfessor Dongsu HanSchool of Electrical EngineeringKAIST
2022.05.10 View 10456 -
Professor Lik-Hang Lee Offers Metaverse Course for Hong Kong Productivity Council
Professor Lik-Hang Lee from the Department of Industrial System Engineering will offer a metaverse course in partnership with the Hong Kong Productivity Council (HKPC) from the Spring 2022 semester to Hong Kong-based professionals.
“The Metaverse Course for Professionals” aims to nurture world-class talents of the metaverse in response to surging demand for virtual worlds and virtual-physical blended environments. The HKPC’s R&D scientists, consultants, software engineers, and related professionals will attend the course. They will receive a professional certificate on managing and developing metaverse skills upon the completion of this intensive course.
The course will provide essential skills and knowledge about the parallel virtual universe and how to leverage digitalization and industrialization in the metaverse era. The course includes comprehensive modules, such as designing and implementing virtual-physical blended environments, metaverse technology and ecosystems, immersive smart cities, token economies, and intelligent industrialization in the metaverse era.
Professor Lee believes in the decades to come that we will see rising numbers of virtual worlds in cyberspace known as the ‘Immersive Internet’ that will be characterized by high levels of immersiveness, user interactivity, and user-machine collaborations.
“Consumers in virtual worlds will create novel content as well as personalized products and services, becoming as catalyst for ‘hyperpersonalization’ in the next industrial revolution,” he said.
Professor Lee said he will continue offering world-class education related to the metaverse to students in KAIST and professionals from various industrial sectors, as his Augmented Reality and Media Lab will focus on a variety of metaverse topics such as metaverse campuses and industrial metaverses.
The HKPC has worked to address innovative solutions for Hong Kong industries and enterprises since 1967, helping them achieve optimized resource utilization, effectiveness, and cost reduction as well as enhanced productivity and competitiveness in both local and international markets. The HKPC has advocated for facilitating Hong Kong’s reindustrialization powered by Industry 4.0 and e-commerce 4.0 with a strong emphasis on R&D, IoT, AI, digital manufacturing.
The Augmented Reality and Media Lab led by Professor Lee will continue its close partnerships with HKPC and its other partners to help build the epicentre of the metaverse in the region. Furthermore, the lab will fully leverage its well-established research niches in user-centric, virtual-physical cyberspace (https://www.lhlee.com/projects-8 ) to serve upcoming projects related to industrial metaverses, which aligns with the departmental focus on smart factories and artificial intelligence.
2022.04.06 View 9351 -
'Fingerprint' Machine Learning Technique Identifies Different Bacteria in Seconds
A synergistic combination of surface-enhanced Raman spectroscopy and deep learning serves as an effective platform for separation-free detection of bacteria in arbitrary media
Bacterial identification can take hours and often longer, precious time when diagnosing infections and selecting appropriate treatments. There may be a quicker, more accurate process according to researchers at KAIST. By teaching a deep learning algorithm to identify the “fingerprint” spectra of the molecular components of various bacteria, the researchers could classify various bacteria in different media with accuracies of up to 98%.
Their results were made available online on Jan. 18 in Biosensors and Bioelectronics, ahead of publication in the journal’s April issue.
Bacteria-induced illnesses, those caused by direct bacterial infection or by exposure to bacterial toxins, can induce painful symptoms and even lead to death, so the rapid detection of bacteria is crucial to prevent the intake of contaminated foods and to diagnose infections from clinical samples, such as urine. “By using surface-enhanced Raman spectroscopy (SERS) analysis boosted with a newly proposed deep learning model, we demonstrated a markedly simple, fast, and effective route to classify the signals of two common bacteria and their resident media without any separation procedures,” said Professor Sungho Jo from the School of Computing.
Raman spectroscopy sends light through a sample to see how it scatters. The results reveal structural information about the sample — the spectral fingerprint — allowing researchers to identify its molecules. The surface-enhanced version places sample cells on noble metal nanostructures that help amplify the sample’s signals.
However, it is challenging to obtain consistent and clear spectra of bacteria due to numerous overlapping peak sources, such as proteins in cell walls. “Moreover, strong signals of surrounding media are also enhanced to overwhelm target signals, requiring time-consuming and tedious bacterial separation steps,” said Professor Yeon Sik Jung from the Department of Materials Science and Engineering.
To parse through the noisy signals, the researchers implemented an artificial intelligence method called deep learning that can hierarchically extract certain features of the spectral information to classify data. They specifically designed their model, named the dual-branch wide-kernel network (DualWKNet), to efficiently learn the correlation between spectral features. Such an ability is critical for analyzing one-dimensional spectral data, according to Professor Jo.
“Despite having interfering signals or noise from the media, which make the general shapes of different bacterial spectra and their residing media signals look similar, high classification accuracies of bacterial types and their media were achieved,” Professor Jo said, explaining that DualWKNet allowed the team to identify key peaks in each class that were almost indiscernible in individual spectra, enhancing the classification accuracies. “Ultimately, with the use of DualWKNet replacing the bacteria and media separation steps, our method dramatically reduces analysis time.”
The researchers plan to use their platform to study more bacteria and media types, using the information to build a training data library of various bacterial types in additional media to reduce the collection and detection times for new samples.
“We developed a meaningful universal platform for rapid bacterial detection with the collaboration between SERS and deep learning,” Professor Jo said. “We hope to extend the use of our deep learning-based SERS analysis platform to detect numerous types of bacteria in additional media that are important for food or clinical analysis, such as blood.”
The National R&D Program, through a National Research Foundation of Korea grant funded by the Ministry of Science and ICT, supported this research.
-PublicationEojin Rho, Minjoon Kim, Seunghee H. Cho, Bongjae Choi, Hyungjoon Park, Hanhwi Jang, Yeon Sik Jung, Sungho Jo, “Separation-free bacterial identification in arbitrary media via deepneural network-based SERS analysis,” Biosensors and Bioelectronics online January 18, 2022 (doi.org/10.1016/j.bios.2022.113991)
-ProfileProfessor Yeon Sik JungDepartment of Materials Science and EngineeringKAIST
Professor Sungho JoSchool of ComputingKAIST
2022.03.04 View 23088 -
SM CEP Soo-Man Lee to Teach at the KAIST School of Computing
The Founder and Chief Executive Producer of SM Entertainment Soo-Man Lee was appointed as a distinguished visiting professor in the KAIST School of Computing. His three-year term starts on March 1.
KAIST and the SM Entertainment signed an MOU on joint research on the metaverse last year and Lee’s appointment is the extension of their mutual collaborations in fields where technologies converge and will encourage innovative advancements in engineering technology and the entertainment industry.
Lee, who completed a graduate program in computer science at California State University Northridge will give special leadership lectures for both undergraduate and graduate students, and will participate in metaverse-related research as a consultant.
In particular, Professor Lee will participate in joint research with the tentatively named Metaverse Institute affiliated with the KAIST Institute for Artificial Intelligence. The institute will help SM Entertainment stay ahead of the global metaverse market by using the avatars of celebrities, and lend itself to raising the already strong brand power of the K-pop leader.
Professor Lee said, “I am grateful that KAIST, the very cradle of Korea’s science and technology, has given me the opportunity to meet its students as a visiting professor. We will lead the metaverse world, in which Korea is emerging as a market leader, with the excellent contents and technology unique to our country, and work together to lead the future global entertainment market.”
President Kwang-Hyung Lee said, “The ability to expand our limitless creativity in the metaverse is indispensable for us as we adapt to this new era. We hope that the vision and creative insights of Executive Producer Lee, which have allowed him to look ahead into the future of the entertainment contents market, will have a positive and fresh impact on the members of KAIST.”
The global influence and reputation of Executive Producer Lee has been well established through his various awards. He was the first Korean to be listed on Variety500 for five consecutive years from 2017 to 2021. He was also the first Korean awardee of the Asia Game Changer Awards in 2016, the first cultural figure to receive the YoungSan Diplomacy Award in 2017, the only Korean to be listed on the 2020 Billboard Impact List, and he has also received the K-pop Contribution Award at the 10th Gaon Chart Music Awards. He recently introduced Play2Create (P2C), a new interactive and creative culture in which re-creation can be enjoyed like a game using IP, and is leading the establishment of the P2C ecosystem.
2022.03.03 View 6742 -
AI Light-Field Camera Reads 3D Facial Expressions
Machine-learned, light-field camera reads facial expressions from high-contrast illumination invariant 3D facial images
A joint research team led by Professors Ki-Hun Jeong and Doheon Lee from the KAIST Department of Bio and Brain Engineering reported the development of a technique for facial expression detection by merging near-infrared light-field camera techniques with artificial intelligence (AI) technology.
Unlike a conventional camera, the light-field camera contains micro-lens arrays in front of the image sensor, which makes the camera small enough to fit into a smart phone, while allowing it to acquire the spatial and directional information of the light with a single shot. The technique has received attention as it can reconstruct images in a variety of ways including multi-views, refocusing, and 3D image acquisition, giving rise to many potential applications.
However, the optical crosstalk between shadows caused by external light sources in the environment and the micro-lens has limited existing light-field cameras from being able to provide accurate image contrast and 3D reconstruction.
The joint research team applied a vertical-cavity surface-emitting laser (VCSEL) in the near-IR range to stabilize the accuracy of 3D image reconstruction that previously depended on environmental light. When an external light source is shone on a face at 0-, 30-, and 60-degree angles, the light field camera reduces 54% of image reconstruction errors. Additionally, by inserting a light-absorbing layer for visible and near-IR wavelengths between the micro-lens arrays, the team could minimize optical crosstalk while increasing the image contrast by 2.1 times.
Through this technique, the team could overcome the limitations of existing light-field cameras and was able to develop their NIR-based light-field camera (NIR-LFC), optimized for the 3D image reconstruction of facial expressions. Using the NIR-LFC, the team acquired high-quality 3D reconstruction images of facial expressions expressing various emotions regardless of the lighting conditions of the surrounding environment.
The facial expressions in the acquired 3D images were distinguished through machine learning with an average of 85% accuracy – a statistically significant figure compared to when 2D images were used. Furthermore, by calculating the interdependency of distance information that varies with facial expression in 3D images, the team could identify the information a light-field camera utilizes to distinguish human expressions.
Professor Ki-Hun Jeong said, “The sub-miniature light-field camera developed by the research team has the potential to become the new platform to quantitatively analyze the facial expressions and emotions of humans.” To highlight the significance of this research, he added, “It could be applied in various fields including mobile healthcare, field diagnosis, social cognition, and human-machine interactions.”
This research was published in Advanced Intelligent Systems online on December 16, under the title, “Machine-Learned Light-field Camera that Reads Facial Expression from High-Contrast and Illumination Invariant 3D Facial Images.” This research was funded by the Ministry of Science and ICT and the Ministry of Trade, Industry and Energy.
-Publication“Machine-learned light-field camera that reads fascial expression from high-contrast and illumination invariant 3D facial images,” Sang-In Bae, Sangyeon Lee, Jae-Myeong Kwon, Hyun-Kyung Kim. Kyung-Won Jang, Doheon Lee, Ki-Hun Jeong, Advanced Intelligent Systems, December 16, 2021 (doi.org/10.1002/aisy.202100182)
ProfileProfessor Ki-Hun JeongBiophotonic LaboratoryDepartment of Bio and Brain EngineeringKAIST
Professor Doheon LeeDepartment of Bio and Brain EngineeringKAIST
2022.01.21 View 13876 -
KAIST ISPI Releases Report on the Global AI Innovation Landscape
Providing key insights for building a successful AI ecosystem
The KAIST Innovation Strategy and Policy Institute (ISPI) has launched a report on the global innovation landscape of artificial intelligence in collaboration with Clarivate Plc. The report shows that AI has become a key technology and that cross-industry learning is an important AI innovation. It also stresses that the quality of innovation, not volume, is a critical success factor in technological competitiveness.
Key findings of the report include:
• Neural networks and machine learning have been unrivaled in terms of scale and growth (more than 46%), and most other AI technologies show a growth rate of more than 20%.
• Although Mainland China has shown the highest growth rate in terms of AI inventions, the influence of Chinese AI is relatively low. In contrast, the United States holds a leading position in AI-related inventions in terms of both quantity and influence.
• The U.S. and Canada have built an industry-oriented AI technology development ecosystem through organic cooperation with both academia and the Government. Mainland China and South Korea, by contrast, have a government-driven AI technology development ecosystem with relatively low qualitative outputs from the sector.
• The U.S., the U.K., and Canada have a relatively high proportion of inventions in robotics and autonomous control, whereas in Mainland China and South Korea, machine learning and neural networks are making progress. Each country/region produces high-quality inventions in their predominant AI fields, while the U.S. has produced high-impact inventions in almost all AI fields.
“The driving forces in building a sustainable AI innovation ecosystem are important national strategies. A country’s future AI capabilities will be determined by how quickly and robustly it develops its own AI ecosystem and how well it transforms the existing industry with AI technologies. Countries that build a successful AI ecosystem have the potential to accelerate growth while absorbing the AI capabilities of other countries. AI talents are already moving to countries with excellent AI ecosystems,” said Director of the ISPI Wonjoon Kim.
“AI, together with other high-tech IT technologies including big data and the Internet of Things are accelerating the digital transformation by leading an intelligent hyper-connected society and enabling the convergence of technology and business. With the rapid growth of AI innovation, AI applications are also expanding in various ways across industries and in our lives,” added Justin Kim, Special Advisor at the ISPI and a co-author of the report.
2021.12.21 View 9497 -
Brain-Inspired Highly Scalable Neuromorphic Hardware Presented
Neurons and synapses based on single transistor can dramatically reduce the hardware cost and accelerate the commercialization of neuromorphic hardware
KAIST researchers fabricated a brain-inspired highly scalable neuromorphic hardware by co-integrating single transistor neurons and synapses. Using standard silicon complementary metal-oxide-semiconductor (CMOS) technology, the neuromorphic hardware is expected to reduce chip cost and simplify fabrication procedures.
The research team led by Yang-Kyu Choi and Sung-Yool Choi produced a neurons and synapses based on single transistor for highly scalable neuromorphic hardware and showed the ability to recognize text and face images. This research was featured in Science Advances on August 4.
Neuromorphic hardware has attracted a great deal of attention because of its artificial intelligence functions, but consuming ultra-low power of less than 20 watts by mimicking the human brain. To make neuromorphic hardware work, a neuron that generates a spike when integrating a certain signal, and a synapse remembering the connection between two neurons are necessary, just like the biological brain. However, since neurons and synapses constructed on digital or analog circuits occupy a large space, there is a limit in terms of hardware efficiency and costs. Since the human brain consists of about 1011 neurons and 1014 synapses, it is necessary to improve the hardware cost in order to apply it to mobile and IoT devices.
To solve the problem, the research team mimicked the behavior of biological neurons and synapses with a single transistor, and co-integrated them onto an 8-inch wafer. The manufactured neuromorphic transistors have the same structure as the transistors for memory and logic that are currently mass-produced. In addition, the neuromorphic transistors proved for the first time that they can be implemented with a ‘Janus structure’ that functions as both neuron and synapse, just like coins have heads and tails.
Professor Yang-Kyu Choi said that this work can dramatically reduce the hardware cost by replacing the neurons and synapses that were based on complex digital and analog circuits with a single transistor. "We have demonstrated that neurons and synapses can be implemented using a single transistor," said Joon-Kyu Han, the first author. "By co-integrating single transistor neurons and synapses on the same wafer using a standard CMOS process, the hardware cost of the neuromorphic hardware has been improved, which will accelerate the commercialization of neuromorphic hardware,” Han added.This research was supported by the National Research Foundation (NRF) and IC Design Education Center (IDEC).
-PublicationJoon-Kyu Han, Sung-Yool Choi, Yang-Kyu Choi, et al.“Cointegration of single-transistor neurons and synapses by nanoscale CMOS fabrication for highly scalable neuromorphic hardware,” Science Advances (DOI: 10.1126/sciadv.abg8836)
-ProfileProfessor Yang-Kyu ChoiNano-Oriented Bio-Electronics Labhttps://sites.google.com/view/nobelab/
School of Electrical EngineeringKAIST
Professor Sung-Yool ChoiMolecular and Nano Device Laboratoryhttps://www.mndl.kaist.ac.kr/
School of Electrical EngineeringKAIST
2021.08.05 View 12481 -
Prof. Sang Wan Lee Selected for 2021 IBM Academic Award
Professor Sang Wan Lee from the Department of Bio and Brain Engineering was selected as the recipient of the 2021 IBM Global University Program Academic Award. The award recognizes individual faculty members whose emerging science and technology contains significant interest for universities and IBM.
Professor Lee, whose research focuses on artificial intelligence and computational neuroscience, won the award for his research proposal titled A Neuroscience-Inspired Approach for Metacognitive Reinforcement Learning. IBM provides a gift of $40,000 to the recipient’s institution in recognition of the selection of the project but not as a contract for services.
Professor Lee’s project aims to exploit the unique characteristics of human reinforcement learning. Specifically, he plans to examines the hypothesis that metacognition, a human’s ability to estimate their uncertainty level, serves to guide sample-efficient and near-optimal exploration, making it possible to achieve an optimal balance between model-based and model-free reinforcement learning.
He was also selected as the winner of the Google Research Award in 2016 and has been working with DeepMind and University College London to conduct basic research on decision-making brain science to establish a theory on frontal lobe meta-enhance learning.
"We plan to conduct joint research for utilizing brain-based artificial intelligence technology and frontal lobe meta-enhanced learning technology modeling in collaboration with an international research team including IBM, DeepMind, MIT, and Oxford,” Professor Lee said.
2021.06.25 View 13943 -
Research Day Highlights the Most Impactful Technologies of the Year
Technology Converting Full HD Image to 4-Times Higher UHD Via Deep Learning Cited as the Research of the Year
The technology converting a full HD image into a four-times higher UHD image in real time via AI deep learning was recognized as the Research of the Year. Professor Munchurl Kim from the School of Electrical Engineering who developed the technology won the Research of the Year Grand Prize during the 2021 KAIST Research Day ceremony on May 25. Professor Kim was lauded for conducting creative research on machine learning and deep learning-based image processing.
KAIST’s Research Day recognizes the most notable research outcomes of the year, while creating opportunities for researchers to immerse themselves into interdisciplinary research projects with their peers. The ceremony was broadcast online due to Covid-19 and announced the Ten R&D Achievement of the Year that are expected to make a significant impact.
To celebrate the award, Professor Kim gave a lecture on “Computational Imaging through Deep Learning for the Acquisition of High-Quality Images.” Focusing on the fact that advancements in artificial intelligence technology can show superior performance when used to convert low-quality videos to higher quality, he introduced some of the AI technologies that are currently being applied in the field of image restoration and quality improvement.
Professors Eui-Cheol Shin from the Graduate School of Medical Science and Engineering and In-Cheol Park from the School of Electrical Engineering each received Research Awards, and Professor Junyong Noh from the Graduate School of Culture Technology was selected for the Innovation Award. Professors Dong Ki Yoon from the Department of Chemistry and Hyungki Kim from the Department of Mechanical Engineering were awarded the Interdisciplinary Award as a team for their joint research.
Meanwhile, out of KAIST’s ten most notable R&D achievements, those from the field of natural and biological sciences included research on rare earth element-platinum nanoparticle catalysts by Professor Ryong Ryoo from the Department of Chemistry, real-time observations of the locational changes in all of the atoms in a molecule by Professor Hyotcherl Ihee from the Department of Chemistry, and an investigation on memory retention mechanisms after synapse removal from an astrocyte by Professor Won-Suk Chung from the Department of Biological Sciences.
Awardees from the engineering field were a wearable robot for paraplegics with the world’s best functionality and walking speed by Professor Kyoungchul Kong from the Department of Mechanical Engineering, fair machine learning by Professor Changho Suh from the School of Electrical Engineering, and a generative adversarial networks processing unit (GANPU), an AI semiconductor that can learn from even mobiles by processing multiple and deep networks by Professor Hoi-Jun Yoo from the School of Electrical Engineering.
Others selected as part of the ten research studies were the development of epigenetic reprogramming technology in tumour by Professor Pilnam Kim from the Department of Bio and Brain Engineering, the development of an original technology for reverse cell aging by Professor Kwang-Hyun Cho from the Department of Bio and Brain Engineering, a heterogeneous metal element catalyst for atmospheric purification by Professor Hyunjoo Lee from the Department of Chemical and Biomolecular Engineering, and the Mobile Clinic Module (MCM): a negative pressure ward for epidemic hospitals by Professor Taek-jin Nam (reported at the Wall Street Journal) from the Department of Industrial Design.
2021.05.31 View 16859 -
Streamlining the Process of Materials Discovery
The materials platform M3I3 reduces the time for materials discovery by reverse engineering future materials using multiscale/multimodal imaging and machine learning of the processing-structure-properties relationship
Developing new materials and novel processes has continued to change the world. The M3I3 Initiative at KAIST has led to new insights into advancing materials development by implementing breakthroughs in materials imaging that have created a paradigm shift in the discovery of materials. The Initiative features the multiscale modeling and imaging of structure and property relationships and materials hierarchies combined with the latest material-processing data.
The research team led by Professor Seungbum Hong analyzed the materials research projects reported by leading global institutes and research groups, and derived a quantitative model using machine learning with a scientific interpretation. This process embodies the research goal of the M3I3: Materials and Molecular Modeling, Imaging, Informatics and Integration.
The researchers discussed the role of multiscale materials and molecular imaging combined with machine learning and also presented a future outlook for developments and the major challenges of M3I3. By building this model, the research team envisions creating desired sets of properties for materials and obtaining the optimum processing recipes to synthesize them.
“The development of various microscopy and diffraction tools with the ability to map the structure, property, and performance of materials at multiscale levels and in real time enabled us to think that materials imaging could radically accelerate materials discovery and development,” says Professor Hong.
“We plan to build an M3I3 repository of searchable structural and property maps using FAIR (Findable, Accessible, Interoperable, and Reusable) principles to standardize best practices as well as streamline the training of early career researchers.”
One of the examples that shows the power of structure-property imaging at the nanoscale is the development of future materials for emerging nonvolatile memory devices. Specifically, the research team focused on microscopy using photons, electrons, and physical probes on the multiscale structural hierarchy, as well as structure-property relationships to enhance the performance of memory devices.
“M3I3 is an algorithm for performing the reverse engineering of future materials. Reverse engineering starts by analyzing the structure and composition of cutting-edge materials or products. Once the research team determines the performance of our targeted future materials, we need to know the candidate structures and compositions for producing the future materials.”
The research team has built a data-driven experimental design based on traditional NCM (nickel, cobalt, and manganese) cathode materials. With this, the research team expanded their future direction for achieving even higher discharge capacity, which can be realized via Li-rich cathodes.
However, one of the major challenges was the limitation of available data that describes the Li-rich cathode properties. To mitigate this problem, the researchers proposed two solutions: First, they should build a machine-learning-guided data generator for data augmentation. Second, they would use a machine-learning method based on ‘transfer learning.’ Since the NCM cathode database shares a common feature with a Li-rich cathode, one could consider repurposing the NCM trained model for assisting the Li-rich prediction. With the pretrained model and transfer learning, the team expects to achieve outstanding predictions for Li-rich cathodes even with the small data set.
With advances in experimental imaging and the availability of well-resolved information and big data, along with significant advances in high-performance computing and a worldwide thrust toward a general, collaborative, integrative, and on-demand research platform, there is a clear confluence in the required capabilities of advancing the M3I3 Initiative.
Professor Hong said, “Once we succeed in using the inverse “property−structure−processing” solver to develop cathode, anode, electrolyte, and membrane materials for high energy density Li-ion batteries, we will expand our scope of materials to battery/fuel cells, aerospace, automobiles, food, medicine, and cosmetic materials.”
The review was published in ACS Nano in March. This study was conducted through collaborations with Dr. Chi Hao Liow, Professor Jong Min Yuk, Professor Hye Ryung Byon, Professor Yongsoo Yang, Professor EunAe Cho, Professor Pyuck-Pa Choi, and Professor Hyuck Mo Lee at KAIST, Professor Joshua C. Agar at Lehigh University, Dr. Sergei V. Kalinin at Oak Ridge National Laboratory, Professor Peter W. Voorhees at Northwestern University, and Professor Peter Littlewood at the University of Chicago (Article title: Reducing Time to Discovery: Materials and Molecular Modeling, Imaging, Informatics, and Integration).This work was supported by the KAIST Global Singularity Research Program for 2019 and 2020.
Publication:
“Reducing Time to Discovery: Materials and Molecular Modeling, Imaging, Informatics and Integration,” S. Hong, C. H. Liow, J. M. Yuk, H. R. Byon, Y. Yang, E. Cho, J. Yeom, G. Park, H. Kang, S. Kim, Y. Shim, M. Na, C. Jeong, G. Hwang, H. Kim, H. Kim, S. Eom, S. Cho, H. Jun, Y. Lee, A. Baucour, K. Bang, M. Kim, S. Yun, J. Ryu, Y. Han, A. Jetybayeva, P.-P. Choi, J. C. Agar, S. V. Kalinin, P. W. Voorhees, P. Littlewood, and H. M. Lee, ACS Nano 15, 3, 3971–3995 (2021) https://doi.org/10.1021/acsnano.1c00211
Profile:
Seungbum Hong, PhD
Associate Professor
seungbum@kaist.ac.kr
http://mii.kaist.ac.kr
Department of Materials Science and Engineering
KAIST
(END)
2021.04.05 View 15238 -
Deep-Learning and 3D Holographic Microscopy Beats Scientists at Analyzing Cancer Immunotherapy
Live tracking and analyzing of the dynamics of chimeric antigen receptor (CAR) T-cells targeting cancer cells can open new avenues for the development of cancer immunotherapy. However, imaging via conventional microscopy approaches can result in cellular damage, and assessments of cell-to-cell interactions are extremely difficult and labor-intensive. When researchers applied deep learning and 3D holographic microscopy to the task, however, they not only avoided these difficultues but found that AI was better at it than humans were.
Artificial intelligence (AI) is helping researchers decipher images from a new holographic microscopy technique needed to investigate a key process in cancer immunotherapy “live” as it takes place. The AI transformed work that, if performed manually by scientists, would otherwise be incredibly labor-intensive and time-consuming into one that is not only effortless but done better than they could have done it themselves. The research, conducted by the team of Professor YongKeun Park from the Department of Physics, appeared in the journal eLife last December.
A critical stage in the development of the human immune system’s ability to respond not just generally to any invader (such as pathogens or cancer cells) but specifically to that particular type of invader and remember it should it attempt to invade again is the formation of a junction between an immune cell called a T-cell and a cell that presents the antigen, or part of the invader that is causing the problem, to it. This process is like when a picture of a suspect is sent to a police car so that the officers can recognize the criminal they are trying to track down. The junction between the two cells, called the immunological synapse, or IS, is the key process in teaching the immune system how to recognize a specific type of invader.
Since the formation of the IS junction is such a critical step for the initiation of an antigen-specific immune response, various techniques allowing researchers to observe the process as it happens have been used to study its dynamics. Most of these live imaging techniques rely on fluorescence microscopy, where genetic tweaking causes part of a protein from a cell to fluoresce, in turn allowing the subject to be tracked via fluorescence rather than via the reflected light used in many conventional microscopy techniques.
However, fluorescence-based imaging can suffer from effects such as photo-bleaching and photo-toxicity, preventing the assessment of dynamic changes in the IS junction process over the long term. Fluorescence-based imaging still involves illumination, whereupon the fluorophores (chemical compounds that cause the fluorescence) emit light of a different color. Photo-bleaching or photo-toxicity occur when the subject is exposed to too much illumination, resulting in chemical alteration or cellular damage.
One recent option that does away with fluorescent labelling and thereby avoids such problems is 3D holographic microscopy or holotomography (HT). In this technique, the refractive index (the way that light changes direction when encountering a substance with a different density—why a straw looks like it bends in a glass of water) is recorded in 3D as a hologram.
Until now, HT has been used to study single cells, but never cell-cell interactions involved in immune responses. One of the main reasons is the difficulty of “segmentation,” or distinguishing the different parts of a cell and thus distinguishing between the interacting cells; in other words, deciphering which part belongs to which cell.
Manual segmentation, or marking out the different parts manually, is one option, but it is difficult and time-consuming, especially in three dimensions. To overcome this problem, automatic segmentation has been developed in which simple computer algorithms perform the identification.
“But these basic algorithms often make mistakes,” explained Professor YongKeun Park, “particularly with respect to adjoining segmentation, which of course is exactly what is occurring here in the immune response we’re most interested in.”
So, the researchers applied a deep learning framework to the HT segmentation problem. Deep learning is a type of machine learning in which artificial neural networks based on the human brain recognize patterns in a way that is similar to how humans do this. Regular machine learning requires data as an input that has already been labelled. The AI “learns” by understanding the labeled data and then recognizes the concept that has been labelled when it is fed novel data. For example, AI trained on a thousand images of cats labelled “cat” should be able to recognize a cat the next time it encounters an image with a cat in it. Deep learning involves multiple layers of artificial neural networks attacking much larger, but unlabeled datasets, in which the AI develops its own ‘labels’ for concepts it encounters.
In essence, the deep learning framework that KAIST researchers developed, called DeepIS, came up with its own concepts by which it distinguishes the different parts of the IS junction process. To validate this method, the research team applied it to the dynamics of a particular IS junction formed between chimeric antigen receptor (CAR) T-cells and target cancer cells. They then compared the results to what they would normally have done: the laborious process of performing the segmentation manually. They found not only that DeepIS was able to define areas within the IS with high accuracy, but that the technique was even able to capture information about the total distribution of proteins within the IS that may not have been easily measured using conventional techniques.
“In addition to allowing us to avoid the drudgery of manual segmentation and the problems of photo-bleaching and photo-toxicity, we found that the AI actually did a better job,” Professor Park added.
The next step will be to combine the technique with methods of measuring how much physical force is applied by different parts of the IS junction, such as holographic optical tweezers or traction force microscopy.
-Profile
Professor YongKeun Park
Department of Physics
Biomedical Optics Laboratory
http://bmol.kaist.ac.kr
KAIST
2021.02.24 View 14015