1
New
The latest blog posts to take off on Hacker News. 262 posts.
2
Model beats Wall Street analysts in forecasting business financials
MIT researchers have developed an automated machine-learning model that uses probability techniques to significantly outperform human Wall Street analysts in predicting quarterly business sales.
3
4
Beyond L2 Loss – How We Experiment with Loss Functions
Estimating expected time of arrival (ETA) is crucial to what we do at Lyft. Estimates go directly to riders and drivers using our apps, as…
5
6
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.
7
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.
8
Play AI Dungeon 2. Become a Dragon. Eat the Moon
I wrote earlier about a neural net-powered dungeon crawling text adventure game called GPT-2-Adventure in which gameplay is incoherent and dreamlike, as you encounter slippery sign text, circular passages, and unexpected lozenge rooms. A PhD student named Nathan trained the neural net on classic dungeon crawling…
9
Information Theory with TensorFlow
Redirecting to https://www.mukeshmithrakumar.com/blog/deep-learning-with-tf2-probability-and-information-theory/ .
10
11
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.
12
Object-recognition dataset stumped the world’s best computer vision models
When computer vision detectors are turned loose in the real world, their performance noticeably drops. In an effort to close this performance gap, a team of MIT and IBM researchers set out to create a very different kind of object-recognition dataset called ObjectNet.
13
Using machine learning to choose compression algorithms
30% less disk required compared to using the single best strategy
14
Understanding “Deep Double Descent”
Double descent is a puzzling phenomenon in machine learning where increasing model size/training time/data can initially hurt performance, but then i…
15
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.
16
17
DeepSpeech 0.6
The Machine Learning team at Mozilla continues work on DeepSpeech, an automatic speech recognition (ASR) engine which aims to make speech recognition technology and trained models openly available to developers. ...
18
19
Amazon SageMaker Autopilot
Update September 30, 2021 – This post has been edited to remove broken links. Today, we’re extremely happy to launch Amazon SageMaker Autopilot to automatically create the best classification and regression machine learning models, while allowing full control and visibility. In 1959, Arthur Samuel defined machine…
20
Introduction to Bert
Unless you have been out of touch with the Deep Learning world, chances are that you have heard about BERT — it has been the talk of the town for the last one year. At the end of 2018 researchers …
21
Taking ML to production with Rust
Hands-on technical leader, Rust expert.
22
23
Astrophotography with Night Sight on Pixel Phones
Posted by Florian Kainz and Kiran Murthy, Software Engineers, Google Research Taking pictures of outdoor scenes at night has so far been the dom...
24
Machine Learning on Encrypted Data Without Decrypting It
Explore cutting-edge cryptographic techniques for machine learning on encrypted data. Discover how to process sensitive information without decryption, ensuring privacy and security.
25
26
How to Begin a Novel
Last year for National Novel Writing Month I trained a neural net called torch-rnn on 10,096 unique ways to begin a novel. It came up with some intriguing possibilities, my personal favorite being “I am forced to write to my neighbors about the beast.” But many of its sentences used made-up words, or had such weird…
27
BodyPix: Real-Time Person Segmentation in the Browser with Tensorflow.js
The TensorFlow blog contains regular news from the TensorFlow team and the community, with articles on Python, TensorFlow.js, TF Lite, TFX, and more.
28
AI Update, Late 2019
It's been 7 months since my last commentary on the field, and as it became regular appearance in this blog (and in fact many people apparently enjoy this form and keep asking for it),
29
30