Boston

David Bau

Elite
@davidbau

Northeastern professor in machine learning, interpretable deep networks, NLP and vision, ex-Googler. Believes that deep learning should be transparent.

seedrandom. seeded random number generator for Javascript

2.1k

rewriting. Rewriting a Deep Generative Model, ECCV 2020 (oral). Interactive tool to directly edit the rules of a GAN to synthesize scenes with objects added, removed, or altered. Change StyleGANv2 to make extravagant eyebrows, or horses wearing hats.

535

how-to-read-pytorch. Quick, visual, principled introduction to pytorch code through five colab notebooks.

482

dissect. Code for the Proceedings of the National Academy of Sciences 2020 article, "Understanding the Role of Individual Units in a Deep Neural Network"

310

baukit. Python

253

ganseeing. Seeing what a GAN cannot generate. Visualizes and quantifies object classes within scenes that are outside the range of a GAN.

188

covid-19-chart. Chart of current COVID-19 time series data. Enables a variety of county- state- and nation-level comparisons and data exploration.

18

mandelbrot. Updated code for https://mandelbrot.page, an early HTML5 demo of the canvas element. See http://davidbau.com/archives/2009/09/27/mandelbrot.html

18

see. see.js interactive eval panel that allows debugging of nested javascript scope.

15

sidn-handbook. The Structure and Interpretation of Deep Networks Handbook

14

xsrand. Several fast 32-bit xor-shift random number generators implemented in Javascript.

14

conformal. An interactive HTML conformal map viewer.

9

gpwidget. Jupyter Notebook

7

cs7180. CS7180 Interpretability Seminar Course Website + Materials

7

envs. Conda environments for pytorch-oriented deep learning work.

5

splaylist. Splay tree in Javascript, with fast indexing and order statistics. Better than a linked list.

4

jquery-turtle. Turtle Graphics for JQuery

4

quick-netdissect. Lightweight reimplementation of netdissect for pytorch (under development)

4

colabsecrets. A repo for keeping track of colab tricks.

4

webcrush. A utility for minifying and LZW compressing an HTML file.

4

make-full-linux-history. Yoann Padioleau's scripts to graft together a nearly complete history of linux commits as a git repo.

3

nnsight. Python

3

miniplaces. baseline setup for alexnet on miniplaces using pytorch

2

ganclass. Python

2

deeplearnjs. Hardware-accelerated deep learning // machine learning // NumPy library for the web.

2

progressive_growing_of_gans. Progressive Growing of GANs for Improved Quality, Stability, and Variation

2

thisxsite. "This X does not exist" website

1

unlearnable. Jupyter Notebook

1

panoptic-segmentation. Python

1

dalle-flow. A Human-in-the-Loop workflow for creating HD images from text

1

net-intent. Simple experiment to explore a jacobian method for determining hidden unit intent.

1

webhome. Academic website at http://davidbau.com/research/

1

coffee-script. IcedCoffeeScript

1

pytorch-setup. Just to share a conda setup that I use

1

sudokui. A simplified sudoku UI for experimenting with A/B testing: MIT 6.831

1

html5-solitaire-js. An HTML5 Solitaire game optimized for iPad

1
36
Apply