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.
How do you fix CUDA out of memory errors in PyTorch?
viswaretas_kotra profile

How do you fix CUDA out of memory errors in PyTorch?

#pytorch #cuda #machinelearning #deeplearning
Comments
10 min read
LSTM, GRU and LightGBM against a 2-line trend rule: the rule came first
quantooo profile

LSTM, GRU and LightGBM against a 2-line trend rule: the rule came first

#machinelearning #deeplearning #python #datascience
Comments
2 min read
JEPA, Explained: What It Actually Does Differently
bharqav profile

JEPA, Explained: What It Actually Does Differently

#machinelearning #ai #deeplearning #python
1
Comments
9 min read
Tech & AI Synthesis: Experience-Handoff Reinforcement Learning for Recursive Self-Improvement
sharathjapa profile

Tech & AI Synthesis: Experience-Handoff Reinforcement Learning for Recursive Self-Improvement

#ai #tech #deeplearning #multimodal
Comments
3 min read
DPO vs RLHF: which should you use to align a model?
viswaretas_kotra profile

DPO vs RLHF: which should you use to align a model?

#machinelearning #ai #llm #deeplearning
1
Comments
9 min read
How does knowledge distillation work for LLMs?
viswaretas_kotra profile

How does knowledge distillation work for LLMs?

#machinelearning #llm #ai #deeplearning
1
Comments
8 min read
Copying without attention: Fourier readout of a fixed-size wave memory
datatab profile

Copying without attention: Fourier readout of a fixed-size wave memory

#machinelearning #deeplearning #ai #embedded
Comments
22 min read
Why Do AI Models Need High-Dimensional Embeddings?
karam999 profile

Why Do AI Models Need High-Dimensional Embeddings?

#deeplearning #ai #llm #embeddings
3
Comments
2 min read
Beyond Static Layers: The Architecture of Mixture-of-Depths (MoD)
malvintnw profile

Beyond Static Layers: The Architecture of Mixture-of-Depths (MoD)

#ai #deeplearning #transformers #machinelearning
Comments
2 min read
SinkState: Scaling Hybrid LLMs with On-the-Fly SVD and Adaptive Low-Rank States
prabhakar_chaudhary_7afe4 profile

SinkState: Scaling Hybrid LLMs with On-the-Fly SVD and Adaptive Low-Rank States

#ai #machinelearning #llm #deeplearning
Comments
5 min read
Building Road Infrastructure Digital Twins with Computer Vision & Deep Learning
atalaghat profile

Building Road Infrastructure Digital Twins with Computer Vision & Deep Learning

#ai #deeplearning #machinelearning
Comments
3 min read
My depth model was obsessed with the sky. Here's how I made it care about cars.
seemanthraju profile

My depth model was obsessed with the sky. Here's how I made it care about cars.

#computervision #deeplearning #machinelearning #computerscience
1
Comments
5 min read
FlashAttention: Why Tiling Attention Makes Transformers Fast Without Changing the Result
umeshtharukaofficial profile

FlashAttention: Why Tiling Attention Makes Transformers Fast Without Changing the Result

#machinelearning #datascience #ai #deeplearning
Comments
11 min read
Reverse-Engineering the Black Box: The Science of Mechanistic Interpretability
malvintnw profile

Reverse-Engineering the Black Box: The Science of Mechanistic Interpretability

#ai #deeplearning #machinelearning
Comments
3 min read
Praxis-1: How Runway Turned a Video Foundation Model Into a Robot Brain
prabhakar_chaudhary_7afe4 profile

Praxis-1: How Runway Turned a Video Foundation Model Into a Robot Brain

#ai #machinelearning #deeplearning #opensource
Comments
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.