DEV Community

Deep Learning

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

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
DINO-EdgeQuery: Learning Building Edges and Their Connections for GIS-Ready Polygons

DINO-EdgeQuery: Learning Building Edges and Their Connections for GIS-Ready Polygons

Comments
15 min read
Section 1: The dataset and the problem

Section 1: The dataset and the problem

Comments
6 min read
RL 6: Pleasure-Seeking Neurons and the Birth of Backpropagation (1972–1980)

RL 6: Pleasure-Seeking Neurons and the Birth of Backpropagation (1972–1980)

Comments
13 min read
Keeping Two Faces From Swapping Mid-Verse: Identity Preservation in AI Music Videos

Keeping Two Faces From Swapping Mid-Verse: Identity Preservation in AI Music Videos

Comments
4 min read
100,000 Videos in Your Pocket: How Douyin's Recommender Reads Your Whole Life in O(1)

100,000 Videos in Your Pocket: How Douyin's Recommender Reads Your Whole Life in O(1)

Comments
7 min read
Section 3a: f-divergences

Section 3a: f-divergences

Comments
8 min read
Section 1: The dataset and the problem

Section 1: The dataset and the problem

Comments
6 min read
From Attention to a Working Language Model

From Attention to a Working Language Model

Comments 1
13 min read
Why Smaller AI Models Can Win in the Enterprise

Why Smaller AI Models Can Win in the Enterprise

8
Comments
2 min read
GRPO leaves the chatbot and starts fixing OCR, while DPO and GRPO get debugged from the inside

GRPO leaves the chatbot and starts fixing OCR, while DPO and GRPO get debugged from the inside

Comments
6 min read
EmbeddingGemma 2: How Google's Open Multimodal Embedding Model Works

EmbeddingGemma 2: How Google's Open Multimodal Embedding Model Works

Comments
5 min read
Only 3% of the Brain Wakes Up: The Mixture-of-Experts Playbook Behind September's Biggest Models

Only 3% of the Brain Wakes Up: The Mixture-of-Experts Playbook Behind September's Biggest Models

Comments
6 min read
Fine-tuning EfficientNetB0 for 104 flower classes: validation vs held-out test scores, honestly

Fine-tuning EfficientNetB0 for 104 flower classes: validation vs held-out test scores, honestly

Comments
2 min read
Fault-Tolerant Foundation Models: Training LLMs to Thrive on Unreliable Hardware

Fault-Tolerant Foundation Models: Training LLMs to Thrive on Unreliable Hardware

Comments
5 min read
The Model That Doesn't Talk

The Model That Doesn't Talk

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