4951
New
The latest blog posts to take off on Hacker News. 6,335 posts.
4952
Deep Learning in the Real World: Dealing with Non-Differentiable Loss Functions
Over the past few years, deep learning has been taking by storm many industries. From voice recognition to image analysis and synthesis, neural networks have turned out to be very efficient at solv…
4953
4954
The FBI Is Tracking Our Faces in Secret, and We’re Suing
There can be no accountability if there is no transparency.
4955
The Machine Learning Software Engineering Interview
Iterations on revealing recurring patterns of thought, feeling, and behavior
4956
4957
Grandmaster level in StarCraft II using multi-agent reinforcement learning
AlphaStar is the first AI to reach the top league of a widely popular esport without any game restrictions. This January, a preliminary version of AlphaStar challenged two of the world's top players in StarCraft II, one of the most enduring and popular real-time strategy video games of all time. Since then, we have…
4958
4959
ML from Scratch, Part 2: Logistic Regression (2018)
In this second installment of the machine learning from scratch we switch the point of view from regression to classification: instead of estimating a number, we will be trying to guess which of 2 possible classes a given input belongs to. A modern example is looking at a photo and deciding if its a cat or a dog.
4960
Using Deep Learning to Predict the Olfactory Properties of Molecules
Posted by Alexander B Wiltschko, Senior Research Scientist, Google Research Smell is a sense shared by an incredible range of living organisms, a...
4961
Applying BERT models to Search
How new advances in the science of language understanding will help you find more useful information in Search.
4962
Quantum supremacy: the gloves are off
Links:Google paper in NatureNew York Times articleIBM paper and blog post responding to Google’s announcementBoaz Barak’s new post: “Boaz’s inferior classical inferiority FA…
4963
Weaponizing and Gamifying AI for WiFi Hacking: Presenting Pwnagotchi 1.0.0
This is the story of a summer project that started out of boredom and that evolved into something incredibly fun and unique. It is also the story of how that p…
4964
4965
ML From Scratch, Part 1: Linear Regression
To kick off this series, will start with something simple yet foundational: linear regression via ordinary least squares. While not particularly exciting, linear regression finds widespread use both as a standalone learning algorithm and as a building block in more advanced learning algorithms.
4966
Video Architecture Search
Posted by Michael S. Ryoo, Research Scientist and AJ Piergiovanni, Student Researcher, Robotics at Google Video understanding is a challenging pr...
4967
Google and Ambient Computing
Google presented a vision of ambient computing that goes beyond the smartphone. The company is well-placed, but faces challenges both in the marketplace and in the mirror.
4968
DuckDuckGo Search Improvements
We're excited to share several improvements to DuckDuckGo Search that should make your searching not only more effective, but also a more pleasant experience.
4969
Solving the Rubik’s cube with a robot hand
We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic Domain Randomization (ADR). The system can handle situations it…
4970
4971
Shareable Jupyter Notebooks That Run on Free Cloud GPUs
Gradient Community Notebooks provide free GPUs with pre-configured environments for machine learning and deep learning projects.
4972
California Blocks Police Body Cam Use of Face Recognition
The state of California just made it clear: Face recognition surveillance isn’t inevitable. We can — and should — protect our communities from this dystopian technology.
4973
A dumb reason computer vision apps aren’t working: Exif Orientation
I’ve written about lots of computer vision and machine learning projects like object recognition systems and face recognition projects. I…
4974
Successful machine learning models: lessons learned at Booking.com
150 successful machine learning models: 6 lessons learned at Booking.com Bernadi et al., KDD’19 Here’s a paper that will reward careful study for many organisations. We’ve previously looked a…
4975
New chips for machine intelligence
This note summarises details of some of the new silicon chips for machine intelligence. Its aim is to distil the most important implementation and architectural details (at least those that are currently available), to highlight the main differences between them. I’m focusing on chips designed for training since they…
4976
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…
4977
Deep Learning: Our Miraculous Year 1990-1991
Many of the basic ideas behind the Deep Learning Revolution were published three decades ago within fewer than 12 months in our "Annus Mirabilis" 1990-91
4978
Principal Component Analysis
In the previous article in this series we distinguished between two kinds of unsupervised learning (cluster analysis and dimensionality reduction) and discussed the former in some detail. In this installment we turn our attention to the later. In dimensionality reduction we seek a function $f : \mathbb{R}^n \mapsto…
4979
A Gentle Introduction to Bayes’ Theorem for Machine Learning
Bayes Theorem provides a principled way for calculating a conditional probability. It is a deceptively simple calculation, although it can be used to easily calculate the conditional probability of events where intuition often fails. Although it is a powerful tool in the field of probability, Bayes Theorem is also…
4980
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…