Machine learning company Updated 2025-07-16
This section is about companies that primarily specialize in machine learning.
The term "machine learning company" is perhaps not great as it could be argued that any of the Big tech are leaders and sometimes, especially in the case of Google, has a main product that is arguably a form of machine learning.
Most of the companies in this section likely going to be from the AI boom era.
Manifold Updated 2025-07-16
We map each point and a small enough neighbourhood of it to , so we can talk about the manifold points in terms of coordinates.
Does not require any further structure besides a consistent topological map. Notably, does not require metric nor an addition operation to make a vector space.
Manifolds are cool. Especially differentiable manifolds which we can do calculus on.
A notable example of a Non-Euclidean geometry manifold is the space of generalized coordinates of a Lagrangian. For example, in a problem such as the double pendulum, some of those generalized coordinates could be angles, which wrap around and thus are not euclidean.
OAuth Updated 2025-07-16
The fatal flaw of OAuth is that websites have to enable specific providers, they can't just automatically select the correct OAuth for a given email domain. This means that the vast majority of websites will only provide the most widely popular providers such as Google, and the like, which means people won't have decent privacy.
So you are just better off with password logins and a decent password manager.
Polonium isotope Updated 2025-07-16
There are no stable isotopes.
Sony Updated 2025-07-16
Nintendo Updated 2025-07-16
SQL:1999 Updated 2025-07-16
Ubuntu 22.04 Updated 2025-07-16
Tileset Updated 2025-07-16
activatedgeek/LeNet-5 Updated 2025-07-16
This repository contains a very clean minimal PyTorch implementation of LeNet-5 for MNIST.
It trains the LeNet-5 neural network on the MNIST dataset from scratch, and afterwards you can give it newly hand-written digits 0 to 9 and it will hopefully recognize the digit for you.
Ciro Santilli created a small fork of this repo at lenet adding better automation for:
Install on Ubuntu 24.10 with:
sudo apt install protobuf-compiler
git clone https://github.com/activatedgeek/LeNet-5
cd LeNet-5
git checkout 95b55a838f9d90536fd3b303cede12cf8b5da47f
virtualenv -p python3 .venv
. .venv/bin/activate
pip install \
  Pillow==6.2.0 \
  numpy==1.24.2 \
  onnx==1.13.1 \
  torch==2.0.0 \
  torchvision==0.15.1 \
  visdom==0.2.4 \
;
We use our own pip install because their requirements.txt uses >= instead of == making it random if things will work or not.
On Ubuntu 22.10 it was instead:
pip install
  Pillow==6.2.0 \
  numpy==1.26.4 \
  onnx==1.17.0 torch==2.6.0 \
  torchvision==0.21.0 \
  visdom==0.2.4 \
;
Then run with:
python run.py
This script:
  • does a fixed 15 epochs on the training data
  • it then uses the trained net from memory to check accuracy with the test data
  • then it also produces a lenet.onnx ONNX file which contains the trained network, nice!
It throws a billion exceptions because we didn't start the Visdom server, but everything works nevertheless, we just don't get a visualization of the training.
The terminal outputs lines such as:
Train - Epoch 1, Batch: 0, Loss: 2.311587
Train - Epoch 1, Batch: 10, Loss: 2.067062
Train - Epoch 1, Batch: 20, Loss: 0.959845
...
Train - Epoch 1, Batch: 230, Loss: 0.071796
Test Avg. Loss: 0.000112, Accuracy: 0.967500
...
Train - Epoch 15, Batch: 230, Loss: 0.010040
Test Avg. Loss: 0.000038, Accuracy: 0.989300
And the runtime on Ubuntu 22.10, P51 was:
real    2m10.262s
user    11m9.771s
sys     0m26.368s
One of the benefits of the ONNX output is that we can nicely visualize the neural network on Netron:
Figure 1.
Netron visualization of the activatedgeek/LeNet-5 ONNX output
. From this we can see the bifurcation on the computational graph as done in the code at:
output = self.c1(img)
x = self.c2_1(output)
output = self.c2_2(output)
output += x
output = self.c3(output)
This doesn't seem to conform to the original LeNet-5 however?

There are unlisted articles, also show them or only show them.