Implementing neural nets

HOWTOs

The internet is full of guides to training neural nets. Here are some selected highlights.

Michael Nielson has a free online textbook with code examples in python. Christopher Olah’s visual explanations make many things clear.

Andrej’s popular unromantic messy guide to training neural nets in practice has a lot of tips that people tend to rediscover the hard way if they do not get them from him. (I did)

It is allegedly easy to get started with training neural nets. Numerous libraries and frameworks take pride in displaying 30-line miracle snippets that solve your data problems, giving the (false) impression that this stuff is plug and play. … Unfortunately, neural nets are nothing like that. They are not “off-the-shelf” technology the second you deviate slightly from training an ImageNet classifier.

Profiling and performance optimisation

• google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.
• Making Deep Learning go Brrrr From First Principles
• Monitor & Improve GPU Usage for Model Training on Weights & Biases
• Tracking system resource (GPU, CPU, etc.) utilization during training with the Weights & Biases Dashboard
• Algorithms for Modern Hardware - Algorithmica
• pytorch profilers
  • PyTorch Profiler tutorial
  • torch.profiler documentation

NN Software

I have used

• pytorch
• julia
• jax
• Occasionally, reluctantly, Tensorflow

I could use any of the other autodiff systems, such as…

• Theano (Python) (now defunct) was a trailblazer
• Torch (lua) —in practice deprecated in favour of pytorch
• Caffe was popular for a while; have not seen it recently (MATLAB/Python)
• Paddlepaddle is one of Baidu’s NN properties (Python/C++)
• mindspore is Huawei’s framework based on source transformation autodiff, targets interesting edge hardware.
• javascript: see javascript machine learning
• julia: Various autodiff and full-service ML tools.

Tracking experiments

See experiment tracking in ML.

Configuring experiments

See configuring experiments; in practice I use hydra for everything.

pre-computed/trained models

• Caffe format:

  • The Caffe Zoo has lots of nice models, pre-trained on their wiki

  • Here’s a great CV one, Andrej Karpathy’s image captioner, Neuraltalk2

• for the NVC dataset: — pre-trained feature model here)

• Alexnet

• For lasagne: https://github.com/Lasagne/Recipes/tree/master/modelzoo

• For Keras:

  • convnets-keras
  • vgg 16-keras
  • Keras VGG and weights.

Managing axes

A lot of the time managing deep learning is remembering which axis is which. Practically, I have found Einstein convention to solve all my needs.

However, there are alternatives. Alexander Rush argues for NamedTensor. Implementations:

• Native Pytorch
• namedtensor pytorch
• labeledtensor tensorflow

Scaling up

See Gradient descent at scale.

Incoming

• lab-ml/nn: 🧠 Implementations/tutorials of deep learning papers with side-by-side notes; including transformers (original, xl, switch, feedback), optimizers(adam, radam, adabelief), gans(dcgan, cyclegan), reinforcement learning (ppo, dqn), capsnet, sketch-rnn, etc.
• labml.ai Neural Networks