Skip to content

Forem

Deep Learning

This tag is for discussing, sharing articles, and asking questions primarily on deep learning - a subfield of machine learning.

about #deeplearning

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.

Cover image for BIG STEPS TO TRANSFORMER (PART 1): BUILDING THE BIGRAM

Hưng Lê Tiến

Nov 30 '25

BIG STEPS TO TRANSFORMER (PART 1): BUILDING THE BIGRAM

#deeplearning #tutorial #architecture #beginners

13 min read

Arvind SundaraRajan

Nov 30 '25

Unlocking AI's Universal Secrets: Do Neural Networks Think in Fractals?

#machinelearning #deeplearning #ai #neuralnetworks

2 min read

Arvind SundaraRajan

Nov 30 '25

Unlocking Neural Network Secrets: Scale-Invariant Geometry for Smarter AI by Arvind Sundararajan

#machinelearning #deeplearning #neuralnetworks #ai

2 min read

Cover image for How I Built a 6B Image Model That Runs on a 16GB GPU (Z-Image)

Nov 29 '25

How I Built a 6B Image Model That Runs on a 16GB GPU (Z-Image)

#showdev #deeplearning #performance #ai

2 min read

Cover image for Part 9: Generating Simba Network with Rust

Palash Kanti Kundu

Jan 1

Part 9: Generating Simba Network with Rust

#rust #deeplearning #nvidia #devjournal

10 min read

Cover image for Part 8: Proving the Universal Approximation Theorem with Rust

Palash Kanti Kundu

Jan 1

Part 8: Proving the Universal Approximation Theorem with Rust

#deeplearning #rust #devjournal

8 min read

Cover image for Part 7: CUDA Integration with Python

Palash Kanti Kundu

Dec 31 '25

Part 7: CUDA Integration with Python

#deeplearning #cuda #python #devjournal

6 min read

Cover image for How Neural Networks Learn – A Simple Guide to Machine Learning & Deep Learning

Nov 28 '25

How Neural Networks Learn – A Simple Guide to Machine Learning & Deep Learning

#deeplearning #machinelearning #tutorial #beginners

6 min read

Arvind SundaraRajan

Nov 28 '25

Unlocking AI's Inner Geometry: Scale-Agnostic Structures in Neural Networks

#machinelearning #deeplearning #ai #math

2 min read

Cover image for Learn to build a Deep Learning library from scratch in Python and NumPy (autograd, CNNs, ResNets) [free]

zekcrates

Jan 1

Learn to build a Deep Learning library from scratch in Python and NumPy (autograd, CNNs, ResNets) [free]

#deeplearning #python #machinelearning #numpy

1 min read

Cover image for Deep learning through the lens of Felix Klein's Erlangen's

Dec 31 '25

Deep learning through the lens of Felix Klein's Erlangen's

#programming #deeplearning #ai #nepal

5 min read

Arvind SundaraRajan

Nov 28 '25

The Hidden Geometry of AI: A Scale-Free Secret to Smarter Networks

#machinelearning #deeplearning #ai #neuralnetworks

2 min read

Cover image for The Transformer Architecture: A Deep Dive into How LLMs Actually Work

Dec 27 '25

The Transformer Architecture: A Deep Dive into How LLMs Actually Work

#architecture #ai #deeplearning #llm

25 min read

Cover image for I trained a Robot Arm: What I failed to learn.

IBIYEMI Samuel O.

Dec 1 '25

I trained a Robot Arm: What I failed to learn.

#ai #deeplearning #machinelearning #learning

3 min read

Cover image for Open-Weight AI for High-Quality Image Generation & Editing

Sophia

Nov 26 '25

Open-Weight AI for High-Quality Image Generation & Editing

#ai #deeplearning #opensource

4 min read

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