Anupama Bidargaddi·Just nowExpected Value, Variance and Standard Deviation: Understanding the Behavior of Random VariablesImagine training a Machine Learning model several times using different random initializations.
Allu Vamsi Pavan Kumar·Just nowIs Agentic AI in Drug Discovery a Myth?Everyone is building AI agents that can design molecules, analyse biological systems, plan chemical synthesis, and even propose scientific…
Shashank Sane·Just nowIlya’s Mind, Part 1: Learning to PredictHow a decade of work prepared Ilya Sutskever to recognize the transformers, LLMs & the power of compute.
In100 days of pythonbyRay King / 金睿·Just nowDay 45 — 梯度下降家族：SGD、momentum 與 Adam，以及學習率失效的那個精確臨界點程式碼：day 45 on GitHub
Mahendra Kumar Velicheti·1h agoWHAT IF YOUTUBE RECOMMENDED THE PERSON YOU WANT TO BECOME?An idea that could turn the world’s biggest video platform into the most personalised learning engine ever built.
Harshit Dawar·1h agoCatastrophic Forgetting in LLMs & Its Solutions: Fine-Tune Without Losing Skills!Replay, LoRA, EWC, KL anchoring, merging, and RAG explained with Python code, so you can fine-tune on your data without regressions.
Iqra Mahmood·1h agoPrepare Image Data for a CNN in Python: Beginner GuideYour CNN can have the right layers and still receive the wrong data.
Silasyl·3h agoInside the Architectures of Open-Source LLMs: Attention, MoE, Hybrid Layers and QuantizationThis project examines the architectures of twelve open-weight models, ranging from 1.7B to 35B parameters, through the cost each one…
