Free ML E-book Adds LSTM Chapter: Build One From Raw Math in Python
GeostatsGuy · x · 2026-10-22
Professor Michael J. Pyrcz (UT Austin) released a new LSTM chapter in his free online e-book Applied Machine Learning in Python. It covers how networks learn from sequences, builds an LSTM unit gate by gate (forget, input, output), implements it from the underlying math in Python, and walks through a hands-on example with step-by-step diagrams.
More from Research
- ToM2Vec encodes Theory of Mind as vectors, beating baselines in Overcooked agent QA — EliasEskin · 2026-10-22
- CONCERT: Generative Modeling of Spatially Resolved Perturbation Responses — anshulkundaje · 2026-10-22
- ToM2Vec trained via self-play with Qwen3-8B transfers to GPT-5.4 teams, adding 17.3 points — EliasEskin · 2026-10-22
- Probing ToM2Vec: latent vectors beat baselines on belief, desire and action prediction — EliasEskin · 2026-10-22
- ToM2Vec uses continuous theory-of-mind vectors to boost multi-agent coordination across 5 tasks — EliasEskin · 2026-10-22
- Latent beats verbal: ToM2Vec outscores language ToM baseline by 9 points on Overcooked — EliasEskin · 2026-10-22