My Learning Journey in AI, Deep Learning, Research, and Open Source

Description and use

A CS student outlines a structured learning and research plan in AI, deep learning, and open source, detailing work at MRM Research, TDA-based interpretability studies, and GSoC preparation.

Problem

A second‑year CS student seeks to structure and document a learning path in AI, deep learning, research, and open source contributions.

Outcome

The student has established a structured learning and contribution plan, integrating research, skill development, and public documentation.

Workflow

• Join MRM Research and complete task phase
• Study Transformers, GANs, LLMs, and general deep learning concepts
• Conduct research on mechanistic interpretability using TDA and Ball Mapper on SAE feature spaces
• Prepare for GSoC by improving programming skills, learning open‑source workflows, and identifying projects
• Read and implement algorithms from Hands‑On Machine Learning with Scikit‑Learn and PyTorch
• Publish regular posts on concepts, research, experiments, GSoC progress, and lessons learned

Evidence

I've successfully completed my task phase at MRM Research (AI) and am now officially part of the team!

Source

My current research interest lies in Mechanistic Interpretability, particularly exploring how Topological Data Analysis (TDA) can help us understand neural network representations.

Source

I'm investigating the use of Ball Mapper to analyse Sparse Autoencoder (SAE) feature activation spaces.

Source

Another goal I'm actively working towards is Google Summer of Code (GSoC).

Source

I'm also currently reading Hands‑On Machine Learning with Scikit‑Learn, and PyTorch.

Source