5521
New
The latest blog posts to take off on Hacker News. 6,336 posts.
5522
5523
How Adversarial Attacks Work
Emil Mikhailov is the founder of XIX.ai [http://XIX.ai] (YC W17). Roman Trusov is a researcher at XIX.ai. Recent studies by Google Brain have shown that any machine learning classifier can be tricked to give incorrect predictions, and with a little bit of skill, you can get them to give pretty much any result you…
5524
5525
Fooling Neural Networks in the Physical World with 3D Adversarial Objects
We've developed an approach to generate 3D adversarial objects that reliably fool neural networks in the real world, no matter how the objects are looked at.
5526
5527
Eager Execution: An imperative, define-by-run interface to TensorFlow
Posted by Asim Shankar and Wolff Dobson, Google Brain Team UPDATE, April 3 2018: Please see the official user guide for more up-to-date code examp...
5528
An Introduction to Deep Learning for Language Modeling
Language models assign probability values to sequences of words. Those three words that appear right above your keyboard on your phone that try to predict the next word you’ll type are one of the uses of language modeling. In the case shown below, the language model is predicting that “from”, “on” and “it” have a high…
5529
5530
The often-overlooked random forest kernel
Ryan Marcus, assistant professor at the University of Pennsylvania. Using machine learning to build the next generation of data systems.
5531
Language Models, Word2Vec, and Efficient Softmax Approximations
The Word2Vec model has become a standard method for representing words as dense vectors. This is typically done as a preprocessing step, after which the learned vectors are fed into a discriminative model (typically an RNN) to generate predictions such as movie review sentiment, do machine translation, or even…
5532
5533
Learning a hierarchy
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
5534
Speech Recognition Is Not Solved
Ever since Deep Learning hit the scene in speech recognition, word error rates have fallen dramatically. But despite articles you may have read, we still don’t have human-level speech recognition. Speech recognizers have many failure modes. Acknowledging these and taking steps towards solving them is critical to…
5535
A Theory of Sequence Memory in Neocortex
Why neurons have thousands of synapses, a theory of sequence memory in neocortex Hawkins & Ahmad, Front. Neural Circuits 2016 It all began with a fascinating lunchtime conversation with Martin …
5536
5537
5538
Word vectors are awesome but you don’t need a neural network to find them
When I started playing with word2vec four years ago I needed (and luckily had) tons of supercomputer time. But because of advances in our understanding of w...
5539
5540
Hey Siri: An On-Device DNN-Powered Voice Trigger for Apple’s Personal Assistant
The “Hey Siri” feature allows users to invoke Siri hands-free. A very small speech recognizer runs all the time and listens for just those…
5541
Pixel Visual Core: Google’s first custom-designed co-processor
Google’s first custom-designed co-processor for consumer products is built into every Pixel 2. Soon, it will enable more applications to use Pixel 2’s camera for taking …
5542
The Neural Net Tank Urban Legend
AI folklore tells a story about a neural network trained to detect tanks which instead learned to detect time of day; investigating, this probably never happened.
5543
There's No Fire Alarm for Artificial General Intelligence
What is the function of a fire alarm?
5544
5545
Gluon – Deep Learning API from AWS and Microsoft
Post by Dr. Matt Wood Today, AWS and Microsoft announced Gluon, a new open source deep learning interface which allows developers to more easily and quickly build machine learning models, without compromising performance. Gluon provides a clear, concise API for defining machine learning models using a collection of…
5546
Competitive Self-Play
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
5547
5548
Tensorflow sucks
A detailed analysis
5549
NNVM Compiler: A New Open End-To-End Compiler for AI Frameworks
You can choose among multiple artificial intelligence (AI) frameworks to develop AI algorithms. You also have a choice of a wide range of hardware to train and deploy AI models. The diversity of frameworks and hardware is crucial to maintaining the health of the AI ecosystem. This diversity, however, also introduces…
5550