Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Jaward 
posted an update Aug 14
Post
1486
Let’s see JEPA in action🤖
Simplified image-based implementation training on a CPU with live preview support - very satisfying to watch:)

I-JEPA is the image-based version of JEPA (Joint-Embedding Predictive Architecture - an alternative to autoregressive LLM architectures ) pioneered by professor Yann Lecun.

At a higher level, I-JEPA predicts image segment representations (Target) based on representations of other segments within the same image (Context). It consists of three key components: a context encoder, target encoder and a predictor.

Code: https://github.com/Jaykef/ai-algorithms/blob/main/mnist_ijepa.ipynb
In this post