Can Machine Learning Help Us Understand Why?
Machine learning is great at finding correlations in data, but can it ever figure out causation? Such an achievement would be a huge milestone: if algorithms could help us shed light on the causes and effects of different phenomena in complex systems, it would deepen our understanding of the world and unlock more powerful tools to influence it. Yesterday, to a packed room, acclaimed researcher Léon Bottou, now at Facebook’s AI research unit and New York University, laid out a new framework for how we might get there...
Rapid, Dynamic Obstacle Avoidance with an Event-based Camera
In this work, we study the effects that perception latency has on the maximum speed a robot can reach to safely navigate through an unknown cluttered environment. We provide a general analysis that can serve as a baseline for future quantitative reasoning for design trade-offs in autonomous robot navigation...
How Exactly StitchFix's "Tinder for Clothes" Learns Your Style
Chris Moody, Stitch Fix’s manager of data science (and a PhD in astrophysics), wanted a way to get more data, and faster, from customers. That’s why he built his “Tinder for clothes” game prototype and shared it with Stitch Fix employees and stylists. Style Shuffle is more than just a fun game to keep customers entertained between clothing shipments. It’s an extremely effective way to learn about their style, and what they’re most likely to want to wear—and buy. And those learnings have made customers spend more per shipment, even if they haven’t played the game...
A Message From This Week's Sponsor
Data Science Articles & Videos
MixMatch: A Holistic Approach to Semi-Supervised Learning
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that works by guessing low-entropy labels for data-augmented unlabeled examples and mixing labeled and unlabeled data using MixUp...
Adversarial Examples Are Not Bugs, They Are Features
Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial examples can be directly attributed to the presence of non-robust features: features derived from patterns in the data distribution that are highly predictive, yet brittle and incomprehensible to humans. ...
An algorithm wipes clean the criminal pasts of thousands
This month, a judge in California cleared thousands of criminal records with one stroke of his pen. He did it thanks to a ground-breaking new algorithm that reduces a process that took months to mere minutes. The programmers behind it say: we’re just getting started solving America’s urgent problems...
Enabling Factorized Piano Music Generation with the MAESTRO Dataset
Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales. Fortunately, most music is also highly structured and can be represented as discrete note events played on musical instruments. Herein, we show that by using notes as an intermediate representation, we can train a suite of models capable of transcribing, composing, and synthesizing audio waveforms with coherent musical structure on timescales spanning six orders of magnitude...
Few-Shot Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images. While remarkably successful, current methods require access to many images in both source and destination classes at training time. We argue this greatly limits their use. Drawing inspiration from the human capability of picking up the essence of a novel object from a small number of examples and generalizing from there, we seek a few-shot, unsupervised image-to-image translation algorithm that works on previously unseen target classes that are specified, at test time, only by a few example images...
Using AI to predict breast cancer and personalize care
Identifying patients at risk before the disease develops has been a central pillar to breast cancer research and effective early detection programs. A team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Massachusetts General Hospital (MGH) has created a new deep learning model that can predict from a mammogram if a patient is likely to develop breast cancer in the future...
The premier machine learning conference series is back!
Predictive Analytics World (PAW) brings together five co-located industry-specific events in Las Vegas: PAW Business, PAW Financial, PAW Industry 4.0, PAW Healthcare and Deep Learning World, gathering the top practitioners and the leading experts in data science and machine learning. By design, this mega-conference is where to meet the who's who and keep up on the latest techniques, making it the leading machine learning event. On stage: Google, Apple, Uber, Facebook, LinkedIn, Twitter and more...
Want to post here? Email us for details >> email@example.com
Data Scientist - Hearst Magazines - NYC
Hearst Magazine Media is seeking a Data Science Lead to join our Pattern & Shape initiative, a new, innovative B2B insights project that will leverage Hearst first party data, 3rd party partner data and client data to generate disruptive insights for our advertising clients, initially serving the fashion and luxury verticals...
Training & Resources
Normalize CIFAR10 Dataset Tensor
Learn how to use Torchvision Transforms Normalize (transforms.Normalize) to normalize CIFAR10 dataset tensors using the mean and standard deviation of the dataset, via a screencast video and full tutorial transcript...
ABC: Model Datasets for Geometric Deep Learning
Scholars have introduced a new and massive ABC-Dataset comprising a collection of 1 million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is represented through a collection of plainly parametrized curves and surfaces that provide ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction...
Searching for MobileNetV3
We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design...
Reproducible Research with R and R Studio
"a very practical book that teaches good practice in organizing reproducible data analysis and comes with a series of examples..."...
For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page
P.S., Want to reach our audience / fellow readers? Consider sponsoring - grab a spot now; first come first served! All the best, Hannah & Sebastian