Expert Insights: 4 - Comprehensive Guide

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Ivan Zdravkov

Oct 28

What EWC buys you that flat L2 does not

#ai #machinelearning #research #deeplearning

5 min read

Ivan Zdravkov

Oct 28

Catastrophic forgetting, measured

#ai #machinelearning #research #deeplearning

5 min read

Ivan Zdravkov

Oct 28

Blackwell quantisation on my own card

#ai #pytorch #deeplearning #research

5 min read

Umesh Tharuka Malaviarachchi

Oct 28

Mixture of Experts: Why Sparse Routing Scales Models Without Scaling Compute

#machinelearning #datascience #ai #deeplearning

7 min read

Umesh Tharuka Malaviarachchi

Oct 28

Double Descent: Why Bigger Models Can Generalise Better After Getting Worse

#machinelearning #datascience #ai #deeplearning

7 min read

Umesh Tharuka Malaviarachchi

Oct 28

Sharpness-Aware Minimization: Why Flat Minima Generalise Better Than Sharp Ones

#machinelearning #datascience #ai #deeplearning

8 min read

Viswaretas Kotra

Oct 28

How do you train a PyTorch model on multiple GPUs?

#pytorch #machinelearning #deeplearning #gpu

8 min read

Umesh Tharuka Malaviarachchi

Oct 27

Grokking: Why Neural Networks Suddenly Generalise Long After Memorising

#machinelearning #datascience #ai #deeplearning

9 min read

frank chu

Oct 27

Genie 4's real upgrade isn't the graphics. It's the second model watching them.

#ai #deeplearning #google #machinelearning

4 min read

Umesh Tharuka Malaviarachchi

Oct 27

Federated Learning: Why Averaging Model Updates Works - and When It Fails

#machinelearning #datascience #ai #deeplearning

8 min read

Felipe 0liveira

Oct 27

GRPO keeps winning the RL-vs-data argument, and LoRA gets a mechanistic audit

#ai #deeplearning #llm #machinelearning

7 min read

Umesh Tharuka Malaviarachchi

Oct 27

Graph Neural Networks: Why Message Passing Works - and Where It Breaks

#machinelearning #datascience #ai #deeplearning

9 min read

Ivan Zdravkov

Oct 31

How much does an adapter forget?

#ai #machinelearning #research #deeplearning

5 min read

Viswaretas Kotra

Oct 26

What is GRPO, and how do you run GRPO training on GPUs?

#machinelearning #llm #ai #deeplearning

9 min read

Krishanth

Oct 26

I Built EveryO to Understand How Neural Networks Actually Work

#python #machinelearning #deeplearning #opensource

8 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

Deep Learning

What EWC buys you that flat L2 does not

Catastrophic forgetting, measured

Blackwell quantisation on my own card

Mixture of Experts: Why Sparse Routing Scales Models Without Scaling Compute

Double Descent: Why Bigger Models Can Generalise Better After Getting Worse

Sharpness-Aware Minimization: Why Flat Minima Generalise Better Than Sharp Ones

How do you train a PyTorch model on multiple GPUs?

Grokking: Why Neural Networks Suddenly Generalise Long After Memorising

Genie 4's real upgrade isn't the graphics. It's the second model watching them.

Federated Learning: Why Averaging Model Updates Works - and When It Fails

GRPO keeps winning the RL-vs-data argument, and LoRA gets a mechanistic audit

Graph Neural Networks: Why Message Passing Works - and Where It Breaks

How much does an adapter forget?

What is GRPO, and how do you run GRPO training on GPUs?

I Built EveryO to Understand How Neural Networks Actually Work