Gradient Descent, Convex Optimization, Stochastic Methods, Loss Functions

Modern Optimizers – An Alchemist's Notes on Deep Learning
notes.kvfrans.com·1d·
Discuss: Hacker News
🎯Reinforcement Learning
Flag this post
“Understanding Loss Functions and Optimization Algorithms in Artificial Neural Networks(ANNs)”
pub.towardsai.net·5h
λFunctional Programming
Flag this post
Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
arxiv.org·1d
🎯Reinforcement Learning
Flag this post
Revolutionizing Continuous Learning with Nested Neural Networks
dev.to·6h·
Discuss: DEV
📱Edge AI
Flag this post
Deep Learning Without Training
zenodo.org·15h·
Discuss: Hacker News
🔥PyTorch
Flag this post
Hyper-Specific Sub-Field Selection: **Predictive Maintenance of Semiconductor Fabrication Equipment**
dev.to·9h·
Discuss: DEV
🧠Machine Learning
Flag this post
Chebyshev Polynomials are Ferraris for Numerical Programmers
leetarxiv.substack.com·17h·
🔢NumPy
Flag this post
Waterfall Methodology AI: The Smart Evolution of Traditional Project Management
writegenic.ai·19h·
Discuss: DEV
💬Prompt Engineering
Flag this post
Introducing Nested Learning: A new ML paradigm for continual learning
research.google·16h·
Discuss: Hacker News
💬Prompt Engineering
Flag this post
Normalized tensor train decomposition
arxiv.org·1d
🧮Embeddings
Flag this post
Book review: “Build a DeepSeek Model (From Scratch)”
dev.to·1h·
Discuss: DEV
🌳Tree-sitter
Flag this post
Thoughts on Building Reliable Systems
medium.com·5h·
🔄Distributed Systems
Flag this post
Accelerating MySQL Query Optimization via Reinforcement Learning & Hypergraph Analysis
dev.to·1d·
Discuss: DEV
🔍Query Optimization
Flag this post
Adaptive Beamforming Optimization via Multi-Metric Bayesian HyperScore
dev.to·2h·
Discuss: DEV
🔢NumPy
Flag this post
Taming Chaos: Predicting Unpredictable Systems Without Guesswork by Arvind Sundararajan
dev.to·21h·
Discuss: DEV
📊Dynamic Programming
Flag this post
Energy Loss Functions for Physical Systems
arxiv.org·3d
📐Linear Algebra
Flag this post
Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach
arxiv.org·2d
🕸️Graph Theory
Flag this post
Topographical sparse mapping: A training framework for deep learning models
sciencedirect.com·3d·
Discuss: Hacker News
👁️Computer Vision
Flag this post
Why Nonparametric Models Deserve a Second Look
towardsdatascience.com·2d
🧠Machine Learning
Flag this post