Pinned Repositories
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
bfloat16
Convert single precision float to bfloat16 (Brain Floating Point) floating-point format
continuallearning
FacePlus
Udacity's Machine Learning Engineer NanoDegree Final Project
fast_flax
a private fork of flax for experimenting
MOOCs
MOOCs exercises
JAX-Toolbox
JAX-Toolbox
pyprobml
Python code for "Probabilistic Machine learning" book by Kevin Murphy
mjsML's Repositories
mjsML/MOOCs
MOOCs exercises
mjsML/bfloat16
Convert single precision float to bfloat16 (Brain Floating Point) floating-point format
mjsML/continuallearning
mjsML/FacePlus
Udacity's Machine Learning Engineer NanoDegree Final Project
mjsML/fast_flax
a private fork of flax for experimenting
mjsML/flax
Flax is a neural network library for JAX that is designed for flexibility.
mjsML/google-research
Google Research
mjsML/mjsML
mjsML/mjsml.github.io
mjsML/openxla-nvgpu
mjsML/pyprobml
Python code for "Machine learning: a probabilistic perspective" (2nd edition)
mjsML/river
A high-throughput, structured streaming framework built atop Redis Streams. C++ and Python support.
mjsML/seed_rl
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
mjsML/superimport
Simple package to lookup missing packages and autoinstall them.
mjsML/t5x
mjsML/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference.
mjsML/VizDoom-Keras-RL
Reinforcement Learning in Keras on VizDoom
mjsML/xg2xg
by ex-googlers, for ex-googlers - a lookup table of similar tech & services