DEV Community

# neuralnetworks

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Transformer Attention Is Hopfield's 1982 Update Rule (And What That Tells Us About LLM Memory)

Transformer Attention Is Hopfield's 1982 Update Rule (And What That Tells Us About LLM Memory)

2
Comments 2
7 min read
How RNNs Work — Remembering Previous States in Sequential Data

How RNNs Work — Remembering Previous States in Sequential Data

Comments
4 min read
How Neural Networks Work — From Perceptrons to Backpropagation

How Neural Networks Work — From Perceptrons to Backpropagation

Comments
3 min read
Stop Guessing Which Weights Your Neural Network Actually Learned: Deterministic Initialization That Tracks Every Change

Stop Guessing Which Weights Your Neural Network Actually Learned: Deterministic Initialization That Tracks Every Change

Comments
6 min read
How Deep Learning Architectures Evolved — From DNNs to Transformers

How Deep Learning Architectures Evolved — From DNNs to Transformers

Comments
3 min read
Phase transitions in neural network training: what your loss curve isn't telling you

Phase transitions in neural network training: what your loss curve isn't telling you

1
Comments
3 min read
HLLN 2.1 Just Beat CfC on Chaos—And It Used 6 Fewer Parameters. Here’s Why That Matters.

HLLN 2.1 Just Beat CfC on Chaos—And It Used 6 Fewer Parameters. Here’s Why That Matters.

Comments
6 min read
What Deep Learning Really Means — From Neural Networks to Modern AI

What Deep Learning Really Means — From Neural Networks to Modern AI

Comments
4 min read
How Backpropagation Works — From Forward Pass to Gradient Updates

How Backpropagation Works — From Forward Pass to Gradient Updates

Comments
3 min read
Why Activation Functions Matter in Neural Networks

Why Activation Functions Matter in Neural Networks

Comments
3 min read
From Sidelined to Streamlined: Decoding My Apple Watch Metrics (Part 1)

From Sidelined to Streamlined: Decoding My Apple Watch Metrics (Part 1)

Comments
3 min read
Part 5 — How AI Actually Learns: The Training Loop Explained

Part 5 — How AI Actually Learns: The Training Loop Explained

Comments
8 min read
Liquid Neural Networks: The Future of Temporal AI in 2024

Liquid Neural Networks: The Future of Temporal AI in 2024

Comments
4 min read
My Study Notes on Convolutional Neural Networks (CNN)

My Study Notes on Convolutional Neural Networks (CNN)

1
Comments
3 min read
Output Layer Explained — Logits, Softmax, Cross-Entropy, and Why They Work Together

Output Layer Explained — Logits, Softmax, Cross-Entropy, and Why They Work Together

Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.