Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Calculus + AI
🤖 Calculus + AI
Specific
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
131
posts in
5.7
ms
Gram
Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon
🤖
Linear Algebra + AI
Content type:
Blog
tridao.me
·
2d
2 days ago
·
Hacker News
Actions for Gram Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon
Reinventing Entropy
📈
Optimization
Content type:
News
Content type:
Blog
3blue1brown.substack.com
·
4d
4 days ago
·
Substack
Actions for Reinventing Entropy
Multilevel
Stochastic
Gradient
Descent
for Risk-Averse PDE-Constrained Optimization
📈
Optimization
Content type:
Academic
arxiv.org
·
2d
2 days ago
Actions for Multilevel Stochastic Gradient Descent for Risk-Averse PDE-Constrained Optimization
ml-from-scratch-book/code: Companion code for
Machine
Learning
From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.
🤖
Courses about AI + Math
Content type:
Code
github.com
·
2d
2 days ago
·
Hacker News
Actions for ml-from-scratch-book/code: Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.
The Smallest Brain You Can Build: A Perceptron in Python
🤖
Linear Algebra + AI
Content type:
Discussion
news.ycombinator.com
·
2d
2 days ago
·
Hacker News
Actions for The Smallest Brain You Can Build: A Perceptron in Python
Vibe Diaries: Training Nanochat
📈
Optimization
vibediary.dev
·
3d
3 days ago
·
Hacker News
Actions for Vibe Diaries: Training Nanochat
The Loop That Improves Almost Anything
📈
Optimization
Content type:
Blog
mentalfaculty.com
·
3d
3 days ago
·
Hacker News
Actions for The Loop That Improves Almost Anything
Fourier fractal dimension to predict the generalization of deep
neural
networks
📈
Optimization
Content type:
Academic
arxiv.org
·
2d
2 days ago
Actions for Fourier fractal dimension to predict the generalization of deep neural networks
Learning
Fuzzy Logic: Automatic
Rule
Discovery Through Differentiable Circuits
🔄
Backpropagation
metafunctor.com
·
4d
4 days ago
·
DEV
Actions for Learning Fuzzy Logic: Automatic Rule Discovery Through Differentiable Circuits
Unpacking
AI
: The Hardware Behind
AI
🤖
Linear Algebra + AI
Content type:
News
pathtostaff.com
·
5d
5 days ago
·
Hacker News
Actions for Unpacking AI: The Hardware Behind AI
Generalizable self-supervised
learning
for imaging flow cytometry on multi-dataset leukocyte differential
🤖
Linear Algebra + AI
Content type:
Academic
nature.com
·
1d
1 day ago
Actions for Generalizable self-supervised learning for imaging flow cytometry on multi-dataset leukocyte differential
Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
🤖
Linear Algebra + AI
Content type:
Academic
arxiv.org
·
16h
16 hours ago
Actions for Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
What are
AI
parameters — and why does everyone keep talking about billions of them?
🔄
Backpropagation
Content type:
Blog
medium.com
·
2d
2 days ago
Actions for What are AI parameters — and why does everyone keep talking about billions of them?
The sample efficiency black hole
📈
Optimization
Content type:
News
dwarkesh.com
·
3d
3 days ago
·
Hacker News
Actions for The sample efficiency black hole
Last-Iterate
Convergence
of Optimistic Multiplicative Weight Update
🔄
Backpropagation
Content type:
Academic
arxiv.org
·
16h
16 hours ago
Actions for Last-Iterate Convergence of Optimistic Multiplicative Weight Update
Direct Indexing with Exclusions
📈
Optimization
world.hey.com
·
6d
6 days ago
·
Hacker News
Actions for Direct Indexing with Exclusions
princezuda/-RequiemGPT-: Fully open source and open weights built and trained by fable five with one prompt. An experience in how
AI
actually works
🤖
Linear Algebra + AI
Content type:
Code
github.com
·
1d
1 day ago
·
Hacker News
Actions for princezuda/-RequiemGPT-: Fully open source and open weights built and trained by fable five with one prompt. An experience in how AI actually works
Forward-Only Convolutional
Neural
Networks
with Learnable Channel-Class Assignment
🤖
Linear Algebra + AI
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment
Sakana
AI
's Recursive Self-Improvement (RSI) Lab
📈
Optimization
sakana.ai
·
6d
6 days ago
·
Hacker News
Actions for Sakana AI's Recursive Self-Improvement (RSI) Lab
How positive tipping points may be the key to protecting tropical rainforests
🎲
Bayesian Inference
theconversation.com
·
2d
2 days ago
Actions for How positive tipping points may be the key to protecting tropical rainforests
« Page 1
·
Page 3 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help