Browsing Tag
deeplearning
33 posts
From Learning Machine Learning to Competing on Kaggle: My First End-to-End Playground Competition Journey
How I applied Exploratory Data Analysis, Feature Engineering, Pipelines, and Ensemble Models to solve a real-world machine learning…
大语言模型的每个参数到底能储存多少信息
https://www.youtube.com/watch?v=_OTcigj2rwg 这期来自 最佳拍档 的视频解读了一篇发表于 ICML 2026 的重磅论文（由 Meta、DeepMind、康奈尔大学与 NVIDIA 联合完成）[[00:43]]。 视频核心解答了“大语言模型的每个参数到底能储存多少信息”，并从信息论的角度重新定义了 LLM 的“记忆”与“泛化”，主要内容包含以下几个核心重点： 核心要点总结 1. 记忆容量的精确量化：约 3.6 比特/参数…
【红杉播客】AI Neolab–Engram【主攻记忆与持续学习】–分享未来 AI 发展趋势的独特见解
https://www.youtube.com/watch?v=aiR7F4jqjXY 在这期由红杉资本（Sequoia Capital）主持的《Training Data》播客节目中，初创公司 Engram 的联合创始人 Dan Biderman 和 Jessy Lin 深入探讨了 “记忆（Memory）与持续学习（Continual Learning）” 在 AI 领域的核心作用，并分享了他们对未来 AI…
Anthropic’s Fable/Mythos shutdown is the first real model export-control shock
Anthropic’s Fable/Mythos shutdown is the first real model export-control shock The important AI story this week is not…
Como Precificar Opções em Nível Institucional Usando IA (PINNs) e Python
Se você trabalha ou estuda o mercado de derivativos, sabe que a velocidade e a precisão no cálculo…
Did My LoRA Learn Tenacious Style—or Just Memorize Augmented Patterns?
In Week 11 Tenacious-Bench, we trained a LoRA adapter on Tenacious-style B2B sales emails using Supervised Fine-Tuning (SFT).…
Equilibrated adaptive learning rates for non-convex optimization
Train deep learning models faster with a simple tweak: ESGD Struggling to make deep learning train faster? Many…
On the Effects of Idiotypic Interactions for Recommendation Communities inArtificial Immune Systems
How a Body’s Tricks Could Make Your Recommendations Smarter Imagine a suggestion system that borrows ideas from the…
Deep Learning Without Backpropagation
Most modern neural networks learn using backpropagation. It works well, but it has a strange property: learning depends…
Backprop Finally Made Sense When I Reimplemented It in Rust
I never used PyTorch or TensorFlow. My ML background was NumPy and scikit-learn. I could train models, tune…
