181
Machine learning systems are stuck in a rut
Machine learning systems are stuck in a rut Barham & Isard, HotOS’19 In this paper we argue that systems for numerical computing are stuck in a local basin of performance and programmabil…
182
183
AIs Named by AIs
Neural networks can be good at naming things, I’ve discovered. Recently I’ve been experimenting with a neural network called GPT-2, which OpenAI trained on a huge chunk of the internet. Thanks to a colab notebook implementation by Max Woolf, I’m able to fine-tune it on specific lists of data -
184
185
186
Siri, Privacy, and Trust
We should expect Apple to lead the industry on this front, but in fact, they’re far behind.
187
188
A guide to OCR with Tesseract, OpenCV and Python
Dive deep into OCR with Tesseract, including Pytesseract integration, training with custom data, limitations, and comparisons with enterprise solutions.
189
SpaCy v2.2
Version 2.2 of the spaCy Natural Language Processing library is leaner, cleaner and even more user-friendly. In addition to new model packages and features for training, evaluation and serialization, we've made lots of bug fixes, improved debugging and error handling, and greatly reduced the size of the library on…
190
Understanding Convolutions (2014)
neural networks , convolutional neural networks , convolution , math , probability
191
192
193
Neural nets typically contain smaller “subnetworks” that can often learn faster
MIT CSAIL's "Lottery ticket hypothesis" finds that neural networks typically contain smaller subnetworks that can be trained to make equally accurate predictions, and often much more quickly.
194
Applied Machine Learning Is a Meritocracy
When making a start in a new field it is common to feel overwhelmed. You may lack confidence or feel as though you are not good enough or that you are lacking some prerequisite. You will explore these issues in this post and learn that such feelings can lead to actions that can consume a […]
195
196
197
Quantum computers: amazing progress, but probably false supremacy claims
A 2017 cartoon from this post. After the embargo update (Oct 25): Now that I have some answers from the people involved let me make a quick update: 1) I still find the paper unconvincing, specific…
198
199
Learning to prove theorems via interacting with proof assistants
Learning to prove theorems via interacting with proof assistants Yang & Deng, ICML’19 Something a little different to end the week: deep learning meets theorem proving! It’s been a while …
200
Implementing a Convolutional Neural Network Using Only NumPy
A simple walkthrough of deriving backpropagation for CNNs and implementing it from scratch in Python.
201
FastMRI initiative releases neuroimaging data set
As part of the fastMRI research project to use AI to speed up MRI scans, NYU Langone Health is making a new dataset of de-identified brain MRIs available to researchers and Facebook AI is sharing additional tools and resources.
202
Using machine learning to choose compression algorithms
30% less disk required compared to using the single best strategy
203
A Predictive Database
What is a predictive database? A database that lets you query predictions from structured tabular data with no model training step. Learn how predictive databases work, when to use them, and how they compare to traditional ML.
204
Building AI that can master complex cooperative games with hidden information
To advance research on AI that can understand others’ points of view and collaborate effectively, Facebook AI has developed a bot that sets a new state of the art in Hanabi, a card game in which all players work together.
205
206
Language, trees, and geometry in neural networks
Language is made of discrete structures, yet neural networks operate on continuous data: vectors in high-dimensional space. A successful language-processing network must translate this symbolic information into some kind of geometric representation—but in what form? Word embeddings provide two well-known examples…
207
Photos from Crude Sketches: Nvidia's GauGAN Explained Visually
In this article I'll be explaining how GauGAN converts simple blobs of color into photorealistic paintings of landscapes.
208
Mayo Clinic to partner with Google
Google Cloud will be at the cornerstone of Mayo Clinic’s digital transformation as it looks to the cloud to enhance patient and clinician experiences, improve diagnostics and patient outcomes, and expand its unparalleled clinical research.
209
Creating a Starcraft AI – Part 22: Caveat Implementor
First part of this series | Previous | Next |Index In the latter part of the last episode, I outlined two problems I want to solve next. The first is to weigh in the direction of my target when fin…
210