Deep learning without gradient descent, 500 layers, no skip connections

What it does

A deep learning architecture derived from first principles — random function theory and indifference postulates. Архитектура глубокого обучения, выведенная из первых принципов — теории случайных функций и постулатов индифферентности. Bakhvalov, Y. N. (2025). Solving a Machine Learning Regression Problem Based on the Theory of Random Functions. arXiv:2512.12731 Bakhvalov, Y. N. (2025). Polyharmonic Spline Packages: Composition, Efficient Procedures for Computation and Differentiation. arXiv:2512.16718 Bakhvalov, Y. N. (2025). Polyharmonic Cascade. arXiv:2512.17671 Bakhvalov, Y. N. (2025). Initialization of a Polyharmonic Cascade, Launch and Testing. arXiv:2512.19524 Бахвалов Ю. Н. (2024).…from github.com

• 
  Boldly go where Gradient Descent has never gone before with DiscoGrad2024 · github.com · ▲232

  Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this might be interesting to you. We develped DiscoGrad, a tool for automatic differentiation through C++ programs involving input-dependent control flow (e.g., "if (f(x) < c) { ... }", differentiating wrt. x) and randomness. Our initial motivation was to enable the use of gradient descent with simulations, which often rely heavily on such discrete branching. The latter makes plain autodiff mostly useless, since it can only account for the…

• 
  Sonnet2017 · deepmind.google · ▲134

  A new library for constructing neural networks from DeepMind

• 
  Netmind Power2023 · netmind.ai · ▲272

  Hi HN, We just opened public access to Qwen3‑Coder‑480B‑A35B‑Instruct via a REST&#x2F;SDK API. Why it might be interesting: - Fully open-source (Apache‑2.0): https:&#x2F;&#x2F;github.com&#x2F;QwenLM&#x2F;Qwen3-Coder - 480B params (35B active MoE), long context up to 1M tokens with YaRN - Matches Claude Sonnet&#x2F;GPT‑4o on SWE-Bench Verified (81.6%) - Free tier: 100K tokens&#x2F;month

• 
  Multi-GPU Reinforcement Learning in Tensorflow for OpenAI Gym2016 · github.com · ▲58

  Multi-GPU reinforcement learning using Deep Q-Network in TensorFlow for OpenAI Gym - vishar0/dist-dqn

• 
  TensorFlow 1.02018 · tensorflow.org · ▲80

  Open-source machine learning library by Google

• 
  Deep Learning2016 · amazon.com · ▲67

  The textbook for modern machine learning

• 
  /dev/null▲489

  a social network for devs

  Dev tools · 3d ago · dev-null.sh

• 
  Whiteboard (YC W26) – an open-source IDE for thoughtful software design▲423

  open-source IDE for thoughtful software design. Contribute to devdotfast/whiteboard development by creating an account on GitHub.

  Dev tools · 28d ago · github.com

• 
  Reladraw – A diagram language where you decide where to place things▲411

  Contribute to reladraw/reladraw development by creating an account on GitHub.

  Dev tools · 26d ago · github.com

• 
  OpenBot▲362

  Grok Bot alternative: free, local, open-source, multiplayer

  Dev tools · 23d ago · openbot.run

• 
  Talanoa▲346

  Hi HN, I’m a fullstack developer, and honestly, I’ve lost count of how many side projects I’ve worked on over the years. But one idea kept coming back to me: a different kind of email client. It first came to me in 2014: “What if we could handle emails more like conversations?” Every year, I’d revisit this concept in my “Build Notes.” Ten years later, no one had built exactly what I had in mind — so I finally decided to do it myself. That’s how Talanoa was born. I wanted something focused on people, not timelines. I was tired of marking messages as unread just to remember to reply later, or…

  Dev tools · 21d ago · talanoa.email

• 
  CoreSpeed▲332

  One MCP for everything your agents need: apps, memory, tools

  Dev tools · 28d ago · corespeed.io

• IN
  isometric.nyc – giant isometric pixel art map of NYC▲1,325

  Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http:&#x2F;&#x2F;cannoneyed.com&#x2F;projects&#x2F;isometric-nyc

  AI · Jan 2026 · cannoneyed.com

• 
  Cowork▲1,088

  Turn Claude into your digital coworker

  AI · Jan 2026 · claude.com

• 
  DataFast▲867

  Revenue-first analytics

  Growth · Jan 2026 · datafa.st

• 
  OpenClaw▲836

  The AI that actually does things

  AI · Jan 2026 · openclaw.ai

• 
  Kilo Code Reviewer▲799

  Automatic AI-powered code reviews the moment you open a PR

  Dev tools · Jan 2026 · kilo.ai

• 
  PostSyncer▲793

  AI Content Maker, for Social Media Publishing

  AI · Jan 2026 · postsyncer.com