Top
New
🌕
Mougatine
joined
1/2/2018, 3:27:24 PM
has
296
karma
RS @ DeepMind.
Doing distributed stuff, such as DiLoCo and DiPaCo
Recent Posts
Fault Tolerant Llama training
by
Mougatine
on 6/23/2025, 9:30:02 AM with
6
comments
MuLoCo: Muon is a practical inner optimizer for DiLoCo
by
Mougatine
on 5/30/2025, 11:48:01 AM with
0
comments
OpenDiLoCo: Open-Source Framework for Distributed Low-Communication Training
by
Mougatine
on 7/11/2024, 10:08:47 AM with
0
comments
Show HN: Deep Learning for Computer Vision course with colabs and Anki cards
by
Mougatine
on 9/7/2021, 1:50:32 PM with
2
comments
Continual Learning at CVPR 2020
by
Mougatine
on 6/30/2020, 8:30:33 AM with
0
comments
Operation Red Falcon (2015)
by
Mougatine
on 3/30/2020, 11:59:38 AM with
0
comments
Lifelong Learning for Deep Neural Networks (2019)
by
Mougatine
on 12/27/2019, 10:44:32 AM with
0
comments
Seeing Is Not Necessarily Believing: Limitations of GANs for Data Augmentation
by
Mougatine
on 5/26/2019, 5:37:41 PM with
0
comments
Cars detection from satellite imagery with RetinaNet
by
Mougatine
on 6/25/2018, 2:19:25 PM with
0
comments
Human or Company
by
Mougatine
on 6/10/2018, 8:45:59 PM with
0
comments
3 Small but Powerful Convolutional Networks
by
Mougatine
on 5/14/2018, 1:48:33 PM with
0
comments
An Explanation of Densely Connected Convolutional Networks
by
Mougatine
on 5/8/2018, 2:49:27 PM with
0
comments
Amazon launches an Android app in India called “Internet”
by
Mougatine
on 4/25/2018, 9:03:53 AM with
0
comments
Summary of “Deep Learning Scaling Is Predictable, Empirically”
by
Mougatine
on 4/20/2018, 9:58:33 PM with
0
comments
How RoI Pooling and RPN Work in Faster-RCNN
by
Mougatine
on 3/30/2018, 1:41:13 PM with
0
comments
Selective Search Explained
by
Mougatine
on 3/13/2018, 5:02:09 PM with
0
comments
Why Some Clocks Have Been Running Slow in Europe
by
Mougatine
on 3/9/2018, 5:37:39 PM with
0
comments
Efficient Graph-Based Segmentation
by
Mougatine
on 3/9/2018, 5:31:59 PM with
0
comments
A Few Useful Things to Know About Machine Learning
by
Mougatine
on 2/8/2018, 2:22:29 PM with
0
comments
Job One for Quantum Computers: Boost Artificial Intelligence
by
Mougatine
on 2/2/2018, 10:22:05 PM with
0
comments
The case for learned index structures
by
Mougatine
on 1/23/2018, 4:09:33 PM with
0
comments
Data-Intensive Systems for the Next 1000x (2016)
by
Mougatine
on 1/23/2018, 12:34:00 PM with
0
comments
The Morning Paper: CS Papers Explained Every Weekday
by
Mougatine
on 1/14/2018, 10:43:51 AM with
0
comments
Useful Mental Models (2016)
by
Mougatine
on 1/8/2018, 9:43:18 PM with
26
comments
Shut Up and Calculate
by
Mougatine
on 1/2/2018, 4:49:02 PM with
0
comments
Course on Distributed Algorithms
by
Mougatine
on 1/2/2018, 3:33:15 PM with
0
comments