-
Swiss Federal Institute of Technology in Lausanne (EPFL)
- Lausanne, Switzerland
- johnny1188.github.io
Highlights
- Pro
Pinned Loading
-
learning-to-optimize
learning-to-optimize PublicCode for our paper Investigation into the Training Dynamics of Learned Optimizers, 2023.
Jupyter Notebook
-
decoding-brain-activity-thesis
decoding-brain-activity-thesis PublicCode for my bachelor's thesis titled "Decoding visual stimuli from cortical activity using neural networks" (2024)
Python
-
fractional-learning-to-optimize
fractional-learning-to-optimize PublicCombining fractional gradient descent with Learning-to-Optimize method.
Jupyter Notebook 1
-
hierarchical-hypernets
hierarchical-hypernets PublicHierarchical Hypernetworks for Continual Learning.
Python
-
deep-q-learning-driver
deep-q-learning-driver PublicImplementation of Deep reinforcement learning (Q-learning) in a self-made game environment of a highway driver.
Python
-
in-context-learning
in-context-learning PublicPaper Reproduction: General-Purpose In-Context Learning by Meta-Learning Transformers.
If the problem persists, check the GitHub status page or contact support.