How quickly can we build a captcha reader using deep learning? Check out yourself the Captcha cracker built TensorFlow 2.0 and #Keras colab.research.google.com/drive/16y14HuN…

We're living in a cyberpunk future: “Fooling automated surveillance cameras: adversarial patches to attack person detection” arxiv.org/abs/1904.08653

If you replace AI research with 3D printer R&D, this is the equivalent of saying: "we're building a matter photocopier. When we're done we can just mass produce absolutely anything for free & sell at 100% margins". AI is math & engineering. It isn't magic. It isn't a free lunch.

WebGL Fluid Simulation This is so cool. Even works on mobile devices. paveldogreat.github.io/WebGL-Fluid-Si…

EfficientNets: a family of more efficient & accurate image classification models. Found by architecture search and scaled up by one weird trick. Link: arxiv.org/abs/1905.11946 Github: bit.ly/30UojnC Blog: bit.ly/2JKY3qt

ConvNets on microcontrollers (e.g. Arduino Uno). In ranges of ~1cm^2 chips, ~$1 costs, running at ~1mW, and 4 MOPs/Sec, 2KB of RAM (intermediate tensors), and 32KB flash (weights). E.g. even LeNet is 420KB model and 177KB RAM. Very interesting to see this line of work develop.

Here's regression example on the Ames Housing Price dataset. This dataset turns out to be great for demonstrating how to vectorize structured data, and how to handle missing features. colab.research.google.com/drive/127UxEcv… Thanks to Micah for suggesting this dataset!

And the best, it's free!

You don't need to know everything. You don't really need a formal background in this or that -- though it helps. You don't even need a PhD. You do, however, need to be constantly learning. Be curious. Read books. Don't be "too busy" to learn, or otherwise proud of your ignorance

Super excited to be at DeepCon on June 8! We'll look at AlexNet VGG Inception MobileNet ShuffleNet ResNet DenseNet Xception U-Net SqueezeNet YOLO RefineNet The workshop will be recorded, you can find our code on GitHub (Part I: ConvNets.ipynb) Dimitris Katsios github.com/Machine-Learni…

A great topic about open-access ML resources!

The release of the Beta for TensorFlow 2.0 is here! We've closed over 100 issues you reported against the alpha release. Your feedback has helped us get to where we are today, please keep it coming! Get more info here → goo.gle/2IpE5OZ

Evolving Neural Turing Machines (GECCO 2016 🦎) “We introduce an evolvable version of NTM and show that such an approach greatly simplifies the neural model, generalizes better, and does not require accessing the entire memory content at each time-step.” sebastianrisi.com/wp-content/upl…

Chapter 9 of "Deep Learning with JavaScript" was recently released to #MEAP. It covers the basics of generative deep learning (VAE, GAN, & RNN-based sequence generation) and how to train and serve such models in TensorFlow.js. Stan Bileschi François Chollet manning.com/books/deep-lea…

Implementing Pix2Pix GAN models from scratch machinelearningmastery.com/how-to-impleme…

"Study hard what interests you the most in the most undisciplined, irreverent, and original manner possible” - Richard Feynman

Temporal Cycle-Consistency Learning (TCC) is a novel self-supervised method for learning representations that are well-suited for fine-grained temporal labeling of video. Learn how it’s done and download the TCC codebase to try it out for yourself! goo.gle/2YSkA87

Sparse Networks from Scratch: Faster Training without Losing Performance By Tim Dettmers Finds "winning lottery tickets" – sparse configurations with 20% weights and similar performance. SoTA on MNIST, CIFAR-10, and ImageNet-2012 among sparse methods arxiv.org/abs/1907.04840

A Web-based implementation of “Deep Image Prior” using TensorFlow.js warlock.ai/dip/

We built bsuite to do two things: 1. Offer clear, informative, and scalable experiments that capture key issues in RL 2. Study agent behaviour through performance on shared benchmarks You can get started with bsuite in this colab: colab.research.google.com/drive/1rU20zJ2…