Simply put: I'm a senior research scientist at MetaMind, acquired by Salesforce, where I poke datasets with the entropy stick and complain about deep neural networks converging too slowly. I'm passionate about machine learning, open data, and teaching computer science.

Despite the many advances in computing over the past decades, the actual process of writing computer software has not fundamentally changed — a programmer must manually code the exact algorithmic logic of a program in a step-by-step manner using a specialized programming language. Although programming languages have become much more user-friendly over the years, learning how to program is still a major endeavor that most computer users have not undertaken.

In a recent paper, we report our latest work in deep learning for program synthesis, where deep neural networks learn how to generate computer programs based on a user’s intent. The user simply provides a few input/output (I/O) examples to specify the desired program behavior, and the system uses these to generate a corresponding program.

Every week, new papers on Generative Adversarial Networks (GAN) are coming out and it’s hard to keep track of them all, not to mention the incredibly creative ways in which researchers are naming these GANs! You can read more about GANs in this Generative Models post by OpenAI or this overview tutorial in KDNuggets.

So, here’s the current and frequently updated list, from what started as a fun activity compiling all named GANs in this format: Name and Source Paper linked to Arxiv.

We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

Abstract: Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.

A look at the importance of Natural Language Processing by Christopher D. Manning.

In this post we will take you behind the scenes on how we built a state-of-the-art Optical Character Recognition (OCR) pipeline for our mobile document scanner. We used computer vision and deep learning advances such as bi-directional Long Short Term Memory (LSTMs), Connectionist Temporal Classification (CTC), convolutional neural nets (CNNs), and more. In addition, we will also dive deep into what it took to actually make our OCR pipeline production-ready at Dropbox scale.

In this project we will be teaching a neural network to translate from French to English.

Sonnet is a library built on top of TensorFlow for building complex neural networks. The main principle of Sonnet is to first construct Python objects which represent some part of a neural network, and then separately connect these objects into the TensorFlow computation graph.

Chainer is a flexible framework of neural networks for deep learning. This repo is dedicated to improving Chainer performance on CPU, especially in Intel® Xeon® and Intel® Xeon Phi™ processors.

This is the code for the paper Perceptual Losses for Real-Time Style Transfer and Super-Resolution, Justin Johnson, Alexandre Alahi, Li Fei-Fei.

The paper builds on A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge by training feedforward neural networks that apply artistic styles to images. After training, our feedforward networks can stylize images hundreds of times faster than the optimization-based method presented by Gatys et al.

This repository also includes an implementation of instance normalization as described in the paper Instance Normalization: The Missing Ingredient for Fast Stylization by Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. This simple trick significantly improves the quality of feedforward style transfer models.

PyScatWave is a CuPy/PyTorch Scattering implementation. A scattering network is a Convolutional Network with filters predefined to be wavelets that are not learned and it can be used in vision task such as classification of images. The scattering transform can drastically reduce the spatial resolution of the input (e.g. 224x224->14x14) with demonstrably neglible loss in dicriminative power.

The software uses PyTorch + NumPy FFT on CPU, and PyTorch + CuPy + CuFFT on GPU.

When I first started investigating the world of deep learning, I found it very hard to get started. There wasn’t much documentation, and what existed was aimed at academic researchers who already knew a lot of the jargon and background. Thankfully that has changed over the last few years, with a lot more guides and tutorials appearing.

I always loved EC2 for Poets though, and I haven’t seen anything for deep learning that’s aimed at as wide an audience. EC2 for Poets is an explanation of cloud computing that removes a lot of the unnecessary mystery by walking anyone with basic computing knowledge step-by-step through building a simple application on the platform. In the same spirit, I want to show how anyone with a Mac laptop and the ability to use the Terminal can create their own image classifier using TensorFlow, without having to do any coding.

In TensorFlow for Poets, I showed how you could train a neural network to recognize objects using your own custom images. The next step is getting that model into users’ hands, so in this tutorial I’ll show you what you need to do to run it in your own iOS application.

Tensorflow is a powerful open-source software library for machine learning developed by researchers at Google Brain. It has many pre-built functions to ease the task of building different neural networks. Tensorflow allows distribution of computation across different computers, as well as multiple CPUs and GPUs within a single machine. TensorFlow provides a Python API, as well as a less documented C++ API. For this course, we will be using Python.

This course will cover the fundamentals and contemporary usage of the Tensorflow library for deep learning research. We aim to help students understand the graphical computational model of Tensorflow, explore the functions it has to offer, and learn how to build and structure models best suited for a deep learning project. Through the course, students will use Tensorflow to build models of different complexity, from simple linear/logistic regression to convolutional neural network and recurrent neural networks with LSTM to solve tasks such as word embeddings, translation, optical character recognition. Students will also learn best practices to structure a model and manage research experiments.

Deep learning is a field with intense computational requirements and the choice of your GPU will fundamentally determine your deep learning experience. With no GPU this might look like months of waiting for an experiment to finish, or running an experiment for a day or more only to see that the chosen parameters were off. With a good, solid GPU, one can quickly iterate over deep learning networks, and run experiments in days instead of months, hours instead of days, minutes instead of hours. So making the right choice when it comes to buying a GPU is critical. So how do you select the GPU which is right for you? This blog post will delve into that question and will lend you advice which will help you to make choice that is right for you.

The purpose of this book is to help to spread this knowledge among engineers who want to expand their wisdom in the exciting world of Machine Learning. I believe that anyone with an engineering background may find applications of Deep Learning, and Machine Learning in general, valuable to their work.

This repository provides tutorial code for deep learning researchers to learn PyTorch. In the tutorial, most of the models were implemented with less than 30 lines of code. Before starting this tutorial, it is recommended to finish Official Pytorch Tutorial.

A collection of deep learning models using Caffe. Lots of researchers and engineers have made Caffe models for different tasks with all kinds of architectures and data. These models are learned and applied for problems ranging from simple regression, to large-scale visual classification, to Siamese networks for image similarity, to speech and robotics applications.

If you are in the position I was where you are on the edge of building your own deep learning machine but a little unsure of time that you need to invest in getting that setup, this post is for you. And this is inspired by my fellow students, mainly Yad Faeq, Brendan Fortuner and our professor Jeremy Howard.