Deep Learning - DEV Community

Skip to content

DEV Community

Please ensure that any post tagged with #deeplearning is primarily on deep learning while generally can be on machine learning, data science, AI, CS, etc.

Please also be sure that your content adheres to the DEV Code of Conduct and that your comments are constructive and kind.

Conventional machine learning techniques are limited in their ability to automatically transform the raw unstructured data into a suitable internal representation. Deep learning methods are representation learning methods with multiple levels of representation, obtained by composing several simple but non-linear modules that each transform the representation at one level (starting with the raw input) into a representation at a higher, slightly more abstract level - to put it simply - Neural Networks. With the composition of enough such transformations, very complex functions can be learned - a universal approximator.
If you want to share something primarily on deep learning techniques please use #deeplearning tag.

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

Prabhakar Chaudhary

Nov 5

BudgetMix RL: What Multi-Turn Reinforcement Learning Really Improves in LLM Agents

#ai #machinelearning #llm #deeplearning

4 min read

Sharath

Nov 5

Research Synthesis: Inside the Architectures of Open-Source LLMs: Attention, MoE, Hybrid Layers and Quantization

#ai #research #deeplearning #knowledgegraphs

2 min read

Nov 4

Warmup Did Nothing for My Learning Rate — Then It Fully Rescued the Wrong One

#pytorch #machinelearning #deeplearning #hyperparameters

4 min read

Nov 4

My Gradient Clipping Was Never Clipping. It Was Secretly Multiplying My Weight Decay

#pytorch #machinelearning #deeplearning #hyperparameters

4 min read

mujin

Nov 5

Own GPU vs rented GPU vs hosted API: a comparison you can redo in an afternoon

#ai #deeplearning #hardware #tools

3 min read

Syed Abdul Hanan for Logit Solutions AI

Nov 4

Why did deep networks stop learning?

#ai #machinelearning #deeplearning #beginners

5 min read

Syed Abdul Hanan for Logit Solutions AI

Nov 4

Why does every AI start out random?

#ai #machinelearning #deeplearning #beginners

5 min read

Mecky Alvin Tanuwidjaya

Nov 4

The Shift to Test-Time Compute: Why AI is Learning to "Think" Before it Speaks

#ai #machinelearning #deeplearning #technologytrends

3 min read

Wesam Khallaf — Author of PyTorch From Ground Up

Nov 4

Saving and Loading Models in PyTorch: state_dict, Checkpoints and Resuming Training

#deeplearning #pytorch #beginners #machinelearning

13 min read

Marcus ma

Nov 4

A Small Weight Edit Helped Qwen Finish Its Reasoning. That Defines the Result.

#ai #deeplearning #llm #machinelearning

5 min read

Viswaretas Kotra

Nov 4

PPO vs DPO vs GRPO: which RL method should you use?

#machinelearning #ai #llm #deeplearning

8 min read

Akira

Nov 4

GPT-6 AstraがQwen3.5-0.8Bを重みの0.016%編集で修正した方法

#ai #deeplearning #llm #machinelearning

4 min read

Walse

Nov 4

Bagaimana GPT-6 Astra Memperbaiki Qwen3.5-0.8B dengan Mengedit 0,016% Bobotnya

#ai #deeplearning #llm #machinelearning

9 min read

Umesh Tharuka Malaviarachchi

Nov 3

Model Soups: Why Averaging Fine-Tuned Weights Beats Picking the Best One

#machinelearning #datascience #ai #deeplearning

7 min read

Ruvarashe S Nemaramba

Nov 3

The New ML Perspective

#ai #programming #machinelearning #deeplearning

4 min read

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