🔄 Backpropagation - atomwalk12

Loss Landscape Diagnosis for Gradient-Based Gray-Scott System Inversion: Disentangling the Roles of PINN Components

🤖Linear Algebra + AI Academic

arxiv.org·

Unpacking AI: The Hardware Behind AI

🤖Linear Algebra + AI News

pathtostaff.com··Hacker News

What are AI parameters — and why does everyone keep talking about billions of them?

🤖Calculus + AI Blog

medium.com·

Multilevel Stochastic Gradient Descent for Risk-Averse PDE-Constrained Optimization

📈Optimization Academic

arxiv.org·

Tampa Bay tech, entrepreneur, and nerd events list (Monday, June 8 – Sunday, June 14)

🤖Calculus + AI

globalnerdy.com·

Gram Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon

🤖Linear Algebra + AI Blog

tridao.me··Hacker News

Projected Inverse Iteration: An Eigenvalue Approach to Ground-State Computation with Neural Quantum States

🤖Linear Algebra + AI Academic

arxiv.org·

Diverse binding poses of agonistic neurotoxins on human Na v 1.6

🤖Linear Algebra + AI Academic

nature.com

ml-from-scratch-book/code: Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.

🤖Courses about AI + Math Code

github.com··Hacker News

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

🤖Linear Algebra + AI Academic

arxiv.org·

The Untrainable

🤖Calculus + AI News Blog

saranormous.substack.com··Substack

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

📈Optimization Academic

arxiv.org·

Designing Loops That Prompt Coding Agents: The Six I Actually Run

🤖Calculus + AI

cameronwestland.com··Hacker News

Growing Pains of Starting a Secret Society

🤖Calculus + AI Blog

mrmarket.bearblog.dev··Hacker News

Flatland: The Adventures of Gradient Descent with Large Step Sizes

🤖Calculus + AI Academic

arxiv.org·

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

🤖Calculus + AI Academic

arxiv.org·

Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network

🤖Calculus + AI Academic

arxiv.org·

Coalitional Darwinism and the Instrumental Utility of Individuality

Asynchronous AI cuts computing energy by orders of magnitude while learning continuously

Major Types of Machine Learning

Loss Landscape Diagnosis for Gradient-Based Gray-Scott System Inversion: Disentangling the Roles of PINN Components

Unpacking AI: The Hardware Behind AI

What are AI parameters — and why does everyone keep talking about billions of them?

Multilevel Stochastic Gradient Descent for Risk-Averse PDE-Constrained Optimization

Tampa Bay tech, entrepreneur, and nerd events list (Monday, June 8 – Sunday, June 14)

Gram Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon

Projected Inverse Iteration: An Eigenvalue Approach to Ground-State Computation with Neural Quantum States

Diverse binding poses of agonistic neurotoxins on human Na v 1.6

ml-from-scratch-book/code: Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

The Untrainable

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

Designing Loops That Prompt Coding Agents: The Six I Actually Run

Growing Pains of Starting a Secret Society

Flatland: The Adventures of Gradient Descent with Large Step Sizes

Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity

Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network