This is your work, valued

Pittsburgh

Zack Chase Lipton

Elite
@zackchase

Assistant Professor of Machine Learning & Operations Research (CMU).

mxnet-the-straight-dope. An interactive book on deep learning. Much easy, so MXNet. Wow. [Straight Dope is growing up] ---> Much of this content has been incorporated into the new Dive into Deep Learning Book available at https://d2l.ai/.

2.6k

python-wow. Python, so easy, wow!

141

mxnet-slides. Slides from MXNet tutorials

51

icu_rnn. Public repository for multilabel classification of medical diagnoses with LSTM RNNs

42

machine-learning-resources. A (possibly/eventually annotated?) collection of resources (books, demos, lectures, etc) that I personally like for various topics in machine learning.

33

label_shift. A simple algorithm to identify and correct for label shift.

21

reading-list. Tracking books that I {have, currently, or plan to} read

18

gluon-slides. Slides from MXNet Gluon tutorials

17

intrinsic-fear-dqn. Avoiding catastrophic failures in reinforcement learning by learning to shape rewards.

10

label-shift. Detect, quantify, and correct for label shift with black box predictors. Guarantee included.

9

mxnet-docs. Staging ground for overhauling the MXNet documentation

6

beermind. deepx

3

excel-windows-mac-commands. A simple table to cross-reference MAC & PC commands for using MS Excel

3

PyRNN. A general purpose RNN library based on Python & theano.

3

dnn-quant. Tool for building deep / recurrent neural network models for systematic fundamental investing.

2

LatentDirichletAllocation.jl. Implementation of Latent Dirichlet Allocation in Julia.

2

fast_multilabel. GPU-accelerated multilabel classification

1

MusicPerception. A set of experiments to discover the intrinsic capacity of people to differentiate and rank pitch sets.

1

mxnet-notebooks. Notebooks for MXNet

1

fairness-dynamics. Numerical experiments examining various toy economic models relating to selection processes (e.g. hiring).

1

learning_permutations. A set of experiments to determine if it's possible to recover spatial (local) structure in data.

1

DCGAN-tensorflow. A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

1