Myoung Hoon Ha is a postdoctoral researcher at the Center for Neuroscience-inspired Artificial Intelligence (CNAI) at KAIST, working with Prof. Sang Wan Lee. His research focuses on neuroscience-inspired AI, with particular emphasis on predictive coding, iterative inference, and stable learning in deep architectures. His recent work includes Meta-PCN (ICLR 2026), which analyzes and stabilizes failure modes in deep predictive coding networks, and Engram Memory Network (IJCNN 2026), a brain-inspired prototype-based explanation model for image classification. More broadly, he works on temporal sequence modeling, neural and behavioral latent-state modeling, and interpretable learning.

Download CV

Interests
  • Predictive Coding and Iterative Inference
  • Temporal Sequence Modeling
  • Neural and Behavioral Modeling
  • Neuroscience-inspired AI
  • Interpretable Learning
Education

  • Ph.D. in Electrical Engineering and Computer Science, 2019

    Seoul National University

  • B.S. in Information and Computer Science (Minor in Mathematics, summa cum laude), 2010

    Ajou University

Publications

Quickly discover relevant content by filtering publications.
Engram Memory Network: Brain-Inspired Prototype Explanations
International Joint Conference on Neural Networks (IJCNN), 2026 (accepted)
Hyunjun Kim, Myoung Hoon Ha
Engram Memory Network: Brain-Inspired Prototype Explanations
Stable and Scalable Deep Predictive Coding Networks with Meta Prediction Errors
In proceedings of the Fourteenth International Conference on Learning Representations (ICLR), 2026
Myoung Hoon Ha, Hyunjun Kim, Yoondo Sung, Youngha Jo, Min S. Kang, Sang Wan Lee
Stable and Scalable Deep Predictive Coding Networks with Meta Prediction Errors
Learning to Escape: Multi-mode Policy Learning for the Traveling Salesman Problem
In proceedings of the IEEE International Conference on Evolving and Adaptive Intelligent Systems (IEEE-EAIS), Madrid, Spain, 2024
Myoung Hoon Ha, Seunggeun Chi, Sang Wan Lee
Learning to Escape: Multi-mode Policy Learning for the Traveling Salesman Problem
Generalizable perceptual embedding with noise-tuning alignment
In proceedings of the 32nd Annual Computational Neuroscience Meeting (CNS), 2023
Jungwon Ryu, Myoung Hoon Ha, Sang Wan Lee
Project
Generalizable perceptual embedding with noise-tuning alignment
InfoGCN: Representation Learning for Human Skeleton-based Action Recognition
In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Myoung Hoon Ha, Hyung-gun Chi, Seunggeun Chi, Sang Wan Lee, Qixing Huang, Karthik Ramani
Cite Code
InfoGCN: Representation Learning for Human Skeleton-based Action Recognition
Evolutionary meta reinforcement learning for portfolio optimization
In proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2021
Myoung Hoon Ha, Seung-geun Chi, Sangyeop Lee, Yujin Cha, Byung-Ro Moon
Project
Evolutionary meta reinforcement learning for portfolio optimization
Understanding features on evolutionary policy optimizations: feature learning difference between gradient-based and evolutionary policy optimizations
In proceedings of the 35th Annual ACM Symposium on Applied Computing (SAC), 2020
Sangyeop Lee, Myoung Hoon Ha, Byung-Ro Moon
Project
Understanding features on evolutionary policy optimizations: feature learning difference between gradient-based and evolutionary policy optimizations
The Evolution of Neural Network-based Chart Patterns: A Preliminary Study
In proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2017
Myoung Hoon Ha, Byung-Ro Moon
Project
The Evolution of Neural Network-based Chart Patterns: A Preliminary Study
A Genetic Algorithm for Rule-based Chart Pattern Search in Stock Market Prices
In proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2016
Myoung Hoon Ha, Sangyeop Lee, Byung-Ro Moon
Project
A Genetic Algorithm for Rule-based Chart Pattern Search in Stock Market Prices
VLR: A Memory-based Optimization Heuristic
In proceedings of the International Conference on Parallel Problem Solving from Nature (PPSN), 2014
Hansang Yun, Myoung Hoon Ha, Robert Ian McKay
Project
VLR: A Memory-based Optimization Heuristic

Experience

 
 
 
 
 
Center for Neuroscience-inspired AI @ KAIST
Postdoctoral Researcher
Center for Neuroscience-inspired AI @ KAIST
Nov 2019 – Present Daejeon
  • Supervised by professor Sang Wan Lee
 
 
 
 
 
Optus Investment
Certified Investment Manager
Optus Investment
May 2011 – Nov 2019 Seoul
  • Applied evolutionary algorithms and reinforcement learning to develop quantitative trading strategies, leading to publications on pattern discovery, feature learning, and portfolio optimization.
  • Built and operated algorithmic trading systems for a discretionary fund, translating research on pattern recognition and optimization into deployable financial software.
 
 
 
 
 
Pantech
Software Engineer
Pantech
Jan 2010 – Dec 2010 Seoul
  • Developed home-screen applications and widgets for Android smartphones.

Projects

*
All Neuroscience-inspired AI Reinforcement Learning
Neural Value Alignment
MSRA-IITP collaborative project on neuroscience-grounded human-AI value alignment. Drove the core research component (Meta-PCN, ICLR 2026).
Genie Brain: Brain-like Abstraction and Reasoning Engine
Devised core algorithms for brain-inspired abstraction (System 1) and reasoning (System 2). Spearheaded collaborative research on language modeling.
Optimal Frame RTB Algorithm Using Deep Reinforcement Learning
Formulated real-time bidding optimization as an MDP and designed an offline deep RL method based on counterfactual learning.
Brain-inspired AI with Human-like Intelligence
Research on cognitive brain development simulation, noise-tuning alignment, and invariant representation learning inspired by the human visual cortex.
Next-generation AI Based on Neural Circuit Mechanism of Metacognition
Collaborated on large-scale neural-behavioral data collection and analysis using the AVATAR system.
Technical Guidance: SW Algorithm Test
Served as a technical advisor supervising the end-to-end design of software algorithm assessment problems.
ATM Cash Reserves Predictor
Developed a data-driven system to forecast ATM cash withdrawal demand, enabling optimal cash reserve allocation.

Teaching

  • Invited lecture series on reinforcement learning implementation (theory and hands-on coding), Hanyang University IDEC industrial training program (approx. 30 participants), Aug. 2022; Jul. 2023.
  • Short lecture series on NLP and reinforcement learning (6 sessions), KAIST Center for Neuroscience-inspired AI internal seminar, Aug.–Sep. 2022.
  • Guest lecture on applied reinforcement learning for the Brain-inspired Artificial Intelligence graduate course, KAIST, Fall 2021, 2022, 2023.

Invited Talks

  • Disentangled Representation of Social Defeat Trace from Freely Moving Rodent Behavior, Korean AI Association Annual Conference, 2021.
  • Evolutionary Policy Optimization for Control Problems in Computational Finance, Center for Neuroscience-inspired AI Invited Seminar, KAIST, 2019.
  • A Deep Understanding of Artificial Neural Networks, invited talk at AI Research Council, Department of Mathematics, Ajou University, 2017.

Supervision

  • Min S. Kang, Graduate student at KAIST, 2024–present (co-author, ICLR 2026)
  • Hyunjun Kim, Graduate student at Seoul National University, 2024–2025 (co-author, ICLR 2026; IJCNN 2026)
  • Ye Mook Choi, Graduate student at KAIST, 2021–2023
  • Juno Kim, Graduate student at KAIST, 2020–2024
  • Seunggeun Chi, Graduate student at Seoul National University, 2019 (co-author, GECCO 2021; IEEE-EAIS 2024)

Services

Session Chair

  • Microsoft Research Asia x KAIST BCS joint workshop, 2023
  • Neuroscience+AI, Korean AI Association, 2021, 2022
  • Next-generation AI: Towards Human-level Intelligence, 2020

Reviewer

  • ICLR, IJCNN, GECCO, ACAIN

Certificate

Certified Investment Manager
Korea Financial Investment Association (KOFIA) Mar 2011
See certificate

Skills

Programming

Python, C/C++

ML/DL Frameworks

PyTorch, TensorFlow, JAX

Research Areas

Deep Learning, Reinforcement Learning, Evolutionary Computation, Computer Vision, NLP, Representation Learning, Neuroscience-inspired AI

Tools

Git, LaTeX, Linux/Unix, SLURM (HPC)

Languages

Korean (Native), English (Professional)