Hesam Sheikh

AI

How I Studied LLMs in Two Weeks: A Comprehensive Roadmap

Image created by Midjourney. A day-by-day detailed LLM roadmap from beginner to advanced, plus some study tips Hesam Sheikh · Follow Published in Towards Data Science · 8 min read · 3 hours ago — Understanding how LLMs operate under the hood is becoming an essential skill in machine learning. Whether you’re choosing the right model for your application, looking for a general knowledge of the field, or following discussions about LLMs and their potential

Read More »
AI

What We Still Don’t Understand About Machine Learning

Machine Learning unknowns that researchers struggle to understand — from Batch Norm to what SGD hides Hesam Sheikh · Follow Published in Towards Data Science · 11 min read · 12 hours ago — What We Still Don’t Understand About Machine Learning. (by author) It is surprising how some of the basic subjects in machine learning are still unknown by researchers and despite being fundamental and common to use, seem to be mysterious. It’s a

Read More »
AI

Understanding Buffer of Thoughts (BoT) — Reasoning with Large Language Models

A new prompting tool for complex reasoning, compared with Chain of thought (CoT) and Tree of Thought (ToT) Hesam Sheikh · Follow Published in Towards Data Science · 10 min read · 3 hours ago — If you’re not a member, read for free! ✨ Photo by Etienne Girardet on Unsplash Squeezing proficiency in complex reasoning tasks and avoiding hallucinations remains a…

Read More »
AI

Understanding Kolmogorov–Arnold Networks (KAN)

Why KANs are a potential alternative to MPLs and the current landscape of Machine Learning. Let’s go through the paper to find out. Hesam Sheikh · Follow Published in Towards Data Science · 10 min read · 8 hours ago — A new research paper titled KAN: Kolmogorov–Arnold Network has stirred excitement in the Machine Learning community. It presents a fresh perspective on Neural Networks…

Read More »