Ben Chuanlong Du's Blog

It is never too late to learn.

Classification

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

GBM

Neuron Network

Use the backpropagation algorithm to learn parameters. Apply observations 1 by 1, which is a stochastic gradient descent algorithm. The complexity of Neuron Network is related to the …

Data Sources

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

Data Platforms

https://www.oxen.ai/

https://github.com/quiltdata/quilt

https://registry.opendata.aws/

https://www.google.com/publicdata/directory

https://proxycrawl.com

Data for Computer Vison

Data for NLP …

Rust for Machine Learning

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

candle

Candle is a minimalist ML framework for Rust with a focus on easiness of use and on performance (including GPU support).

dfdx

dfdx is an ergonomics & safety focused deep learning …

Hardware for AI

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

TVM for deep learning is kind of like LLVM for programming languages.

Nvidia TensorRT

Embedded/Edge AI

Jetson Nano

Google Coral

Intel Neural Compute Stick 2

https://heartbeat.fritz.ai/edge-tpu-google-coral-usb-accelerator-cf0d79c7ec56 …

Loss Functions for Machine Learning Models

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

Tips and Traps

  1. A Loss function is always non-negative. If you get a negative loss when training a model, there must be something wrong with the code. For example, maybe you …