DEV Community

Deep Learning

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

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
One "+x" That Made 100-Layer Networks Trainable: ResNet Skip Connections

One "+x" That Made 100-Layer Networks Trainable: ResNet Skip Connections

2 min read
Activation Functions: Why Non-Linearity Is Everything

Activation Functions: Why Non-Linearity Is Everything

3 min read
AI Deep Learning: Explained Simply

AI Deep Learning: Explained Simply

2
1
3 min read
Your gradient dies on the way to layer 1 (and how to save it)

Your gradient dies on the way to layer 1 (and how to save it)

1
4 min read
Understanding Backpropagation: Calculating Gradients for Hidden Layer Weights and Biases

Understanding Backpropagation: Calculating Gradients for Hidden Layer Weights and Biases

6
3 min read
Dropout: Switch Off Neurons to Stop Overfitting

Dropout: Switch Off Neurons to Stop Overfitting

1 min read
Free from-scratch deep learning notes: tensors, attention, and a tiny GPT

Free from-scratch deep learning notes: tensors, attention, and a tiny GPT

1 min read
Проект: Модель для классификации рака

Проект: Модель для классификации рака

1 min read
Project: Cancer Classification Model

Project: Cancer Classification Model

1 min read
From Transformer to ChatGPT: How One Paper Changed AI Engineering Forever

From Transformer to ChatGPT: How One Paper Changed AI Engineering Forever

1
3 min read
Atlas Wang 对谈:符号 AI 与神经网络以及金融高频交易的 AI 化

Atlas Wang 对谈:符号 AI 与神经网络以及金融高频交易的 AI 化

3 min read
Understanding Database Relationships: From Relational Models to Star and Snowflake Schemas

Understanding Database Relationships: From Relational Models to Star and Snowflake Schemas

3 min read
Steering Vectors: Changing What an LLM Wants Without Touching Its Weights

Steering Vectors: Changing What an LLM Wants Without Touching Its Weights

2 min read
Batch Normalization: Why It Made Deep Nets Trainable

Batch Normalization: Why It Made Deep Nets Trainable

1 min read
NVIDIA's LocateAnything-3B: The AI Vision Model That Could Redefine Object Detection

NVIDIA's LocateAnything-3B: The AI Vision Model That Could Redefine Object Detection

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