HeyJaredHands-on Geometric Deep Learning
Dive into hands-on Geometric Deep Learning! From manifolds and graph neural networks to Lie groups and point clouds, we blend theory with practical Python tools like PyTorch Geometric & Geomstats.
- Indexed issues, last 90 days
- 8
- Latest publication
- Sep 19, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 8, 2026
Latest issues
JEPA: Breakthrough or Band-Aid? (opens the original)
Read excerpt
Every emerging AI paradigm draws both enthusiastic supporters and detractors; the Joint Embedding Predictive Architecture (JEPA) is no exception. You may wonder how JEPA actually fix the foundational flaws plaguing current deep learning and Large Language Models? This post reviews the JEPA functional design and components to answer this question.<a class="image-link image2 is-viewable-img" href="https://substackcdn.com/image/fetch/$s_!oVjn!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fs
Hands-on Lie Geometry for Data Scientists (opens the original)
Read excerpt
Lie Geometry is a critical element of Geometric Deep Learning and consequentially world models. However the topic can be intimidating to reader with even satisfactory knowledge of differential geometry.This article introduces Lie groups and algebras with intuitive examples before diving into the mathematical formalism and implementation in Python.<a class="image-link image2 is-viewable-img" href="https://substackcdn.com/image/fetch/$s_!a8w9!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2F
The Geometric Future of World Models (opens the original)
Read excerpt
Have you ever wondered how World Models can represent our observed reality—without any built-in knowledge of the physical laws, geometric invariants, and constraints that govern itGeometric Deep Learning (GDL) aggregates and modularizes the mathematical concepts that enable reasoning in the latent space of World Models.<a class="image-link image2 is-viewable-img" href="https://substackcdn.com/image/fetch/$s_!5rez!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack
Fractal Dimension for Configuring Convolutional Networks (opens the original)
Read excerpt
Challenged by the configuration of Convolutional Neural Networks for complex images?Incorporating fractal dimension analysis offers a promising strategy. By quantifying structural complexity, this method aids in rationally configuring essential parameters such as kernel size, padding, and pooling.<a class="image-link image2 is-viewable-img" href="https://substackcdn.com/image/fetch/$s_!1Tk9!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fima
Q & A Answers (opens the original)
Read excerpt
<img alt="" class="sizing-normal" height="699" src="https://substackcdn.com/image/fetch/$s_!neqg!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcb566d88-c4a0-4701-89d1-07393f2c2c81_1010x699.hei
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.