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.
I distilled a 7B vision model into a 2B one for screenshots — and the 7B teacher scored worse

Metric bias against descriptive thoroughness

I distilled a 7B vision model into a 2B one for screenshots — and the 7B teacher scored worse

30
Comments 7
10 min read
Reproducing Chinchilla Scaling on a Budget

Reproducing Chinchilla Scaling on a Budget

1
Comments
3 min read
What Does a Product Data Scientist Actually Do?

What Does a Product Data Scientist Actually Do?

Comments
2 min read
Attention Is All You Need - Part 4

Attention Is All You Need - Part 4

5
Comments
2 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
#6.AI vs ML vs Deep Learning

#6.AI vs ML vs Deep Learning

Comments
2 min read
How Model Distillation Actually Works (and What the 'China Distilled Our Model' Headlines Really Mean)

How Model Distillation Actually Works (and What the 'China Distilled Our Model' Headlines Really Mean)

42
Comments 15
6 min read
Inside Diffusion Models: Why They Replaced GANs

Inside Diffusion Models: Why They Replaced GANs

1
Comments 1
3 min read
Yann LeCun thinks the whole industry is building the wrong thing, and now he has $1B to prove it

Yann LeCun thinks the whole industry is building the wrong thing, and now he has $1B to prove it

Comments
7 min read
Recurrent Neural Networks

Recurrent Neural Networks

Comments
17 min read
Top 5 Reinforcement Learning Environments

Top 5 Reinforcement Learning Environments

Comments
11 min read
Reading the Receipts: How Smarter Privacy Accounting Could Unlock More from Sensitive Data

Reading the Receipts: How Smarter Privacy Accounting Could Unlock More from Sensitive Data

Comments
9 min read
Keras Deserialization Safe Mode: Security Capabilities and Limitations

Keras Deserialization Safe Mode: Security Capabilities and Limitations

Comments
3 min read
Why Your Neural Network Fails Silently and How to Actually Debug It

Why Your Neural Network Fails Silently and How to Actually Debug It

Comments
5 min read
The Eighty-Year Argument: Who Owns World Models?

The Eighty-Year Argument: Who Owns World Models?

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