NYU Deep Learning Spring 2021
-
Updated
Nov 11, 2025 - Jupyter Notebook
NYU Deep Learning Spring 2021
An open-source attempt at training a variant of LeCun's energy-based models (EBM) to reason in latent space and solve Sudoku.
A first-principles exploration of the physics, calculus, and probabilistic graph models required to build agents capable of causal reasoning, energy minimization, and structural extrapolation
Project for Yann Lecun's Deep Learning class. In this project, we train a JEPA world model on a set of pre-collected trajectories from a toy environment involving an agent in two rooms.
Recognizing handwritten digits with classical machine learning with a 97% accuracy and f1-score
Self supervised pre training that learns rich visual representations by predicting masked image patch representations conditioned on language context without pixel reconstruction.
Implementation of the LeNet-5 model proposed by Yann Le Cun in 1998
Deep Learning (with PyTorch)
Develop from scratch deep learning Mnist detector
Add a description, image, and links to the yann-le-cunn topic page so that developers can more easily learn about it.
To associate your repository with the yann-le-cunn topic, visit your repo's landing page and select "manage topics."