When we look very closely at images generated by neural networks, we often see a strange checkerboard pattern of artifacts. It’s more obvious in some cases than others, but a large fraction of recent models exhibit this behavior. Mysteriously, the checkerboard pattern tends to be most prominent in images with strong colors. What’s going on? Read more about Deconvolution and Checkerboard Artifacts — Distill[…]
A popular method for exploring high-dimensional data is something called t-SNE, introduced by van der Maaten and Hinton in 2008. The technique has become widespread in the field of machine learning, since it has an almost magical ability to create compelling two-dimensonal “maps” from data with hundreds or even thousands of dimensions. Although impressive, these Read more about How to Use t-SNE Effectively — Distill[…]
Recurrent neural networks are one of the staples of deep learning, allowing neural networks to work with sequences of data like text, audio and video. They can be used to boil a sequence down into a high-level understanding, to annotate sequences, and even to generate new sequences from scratch! Source: Attention and Augmented Recurrent Neural Read more about Attention and Augmented Recurrent Neural Networks — Distill[…]
The Deep Learning textbook is a resource intended to help students and practitioners enter the field of machine learning in general and deep learning in particular. The online version of the book is now complete and will remain available online for free. Source: Deep Learning
Neural Networks and Deep Learning is a free online book. The book will teach you about: Neural networks, a beautiful biologically-inspired programming paradigm which enables a computer to learn from observational data Deep learning, a powerful set of techniques for learning in neural networks Neural networks and deep learning currently provide the best solutions to Read more about Neural networks and deep learning[…]
Several interactive visualizations of a generative model of handwriting. Some are fun, some are serious. Source: Experiments in Handwriting with a Neural Network — Distill
Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Indeed, in the context of TensorFlow, it’s natural to view tensors (or slices of tensors) as points in space, so almost any TensorFlow system will naturally give rise to various embeddings. To learn more about embeddings and how to train Read more about TensorBoard: Embedding Visualization for Tensorflow[…]
DeepMind Lab is a fully 3D game-like platform tailored for agent-based AI research. It is observed from a first-person viewpoint, through the eyes of the simulated agent. Scenes are rendered with rich science fiction-style visuals. The available actions allow agents to look around and move in 3D. The agent’s “body” is a floating orb. It Read more about Open-sourcing DeepMind Lab[…]
We’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the world’s supply of games, websites and other applications. Universe allows an AI agent to use a computer like a human does: by looking at screen pixels and operating a virtual keyboard and mouse. We must train AI systems on Read more about OpenAI Universe allows your AI to train on games, browsers by looking at screen pixels. Uses Gym (also OSS) for algo devs[…]
“There’s a 60-year-old woman in Tokyo. She was at the University of Tokyo. She had been diagnosed with leukemia six years ago. She was living, but not healthy. So the University of Tokyo ran her genomic sequence through Watson and it was able to ascertain that they were off by one thing. Actually, she had Read more about How IBM Watson saved the life of a woman dying from cancer, exec says – Business Insider[…]
AMD is announcing a new series of Radeon-branded products today, targeted at machine intelligence (AI) and deep learning enterprise applications, called Radeon Instinct. As its name suggests, the new Radeon Instinct line of products are comprised of GPU-based solutions for deep learning, inference, and training. The new GPUs are also complemented by a free, open-source library Read more about AMD Introduces Radeon Instinct Machine Intelligence And Deep Learning Accelerators[…]
The Chicago Face Database was developed at the University of Chicago by Debbie S. Ma, Joshua Correll, and Bernd Wittenbrink. The CFD is intended for use in scientific research. It provides high-resolution, standardized photographs of male and female faces of varying ethnicity between the ages of 17-65. Extensive norming data are available for each individual Read more about Chicago Face Database[…]
Source: China has now eclipsed US in AI / deep-learning research, robotics and VC funding (government-backed $338 billion) · GitHub
TensorFlow™ is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile Read more about TensorFlow — Googles’ Open Source Software Library for Machine Intelligence[…]
If you can translate from A to B and from B to C can you translate from A to C without learning the translations directly? Well yes you can. So the translate AI has created its’ own language B (we think) that can function as a midpoint between not only A and C, but also Read more about Google’s AI translation tool seems to have invented its own secret internal language[…]
Using a deep convolutional neural network with residual connections, Miles Deep quickly classifies each second of a pornographic video into 6 categories based on sexual act with 95% accuracy. Then it uses that classification to automatically edit the video. It can remove all the scenes not containing sexual contact, or edit out just a specific Read more about Miles Deep – AI Porn Video Editor[…]
AI Experiments is a showcase for simple experiments that let anyone play with artificial intelligence and machine learning in hands-on ways, through pictures, drawings, language, music, and more. Source: A.I. Experiments
The Photo Scan app launched by Google today for iOS and Android lets you scan printed photos in just a couple of seconds, using machine learning to correct imperfections in the capture process that they look great every time. Here’s how it works: Download the app, and open it up. You’ll see a viewfinder. Hold Read more about Google’s Photo Scan App Makes Backing Up Old Snapshots Easy as Hell[…]
Great article about AI being used to create musical art, with links. The music sounds good too! Source: Top of the bots: This AI isn’t a cold, cruel killing machine – it’s a pop music hit machine
The Microsoft Cognitive Toolkit—previously known as CNTK—helps you harness the intelligence within massive datasets through deep learning. Source: The Microsoft Cognitive Toolkit – Microsoft Research They also offer RESTful APIs on another site, Cognitive Services, with applications you can tap into and APIs for vison, speech, language, knowledge and search. They usually offer free testing, Read more about The Microsoft Cognitive Toolkit now on Github: deep learning AI that recognises human speech at very low error rates[…]
It had been three months since Roman Mazurenko, Kuyda’s closest friend, had died. Kuyda had spent that time gathering up his old text messages, setting aside the ones that felt too personal, and feeding the rest into a neural network built by developers at her artificial intelligence startup. She had struggled with whether she was Read more about Someone built an AI chatbot from a text message database of a dead man, works quite well[…]
The agency, Hallman said, has significantly improved its “anticipatory intelligence,” using a mesh of sophisticated algorithms and analytics against complex systems to better predict the flow of everything from illicit cash to extremists around the globe. Deep learning and other forms of machine learning can help analysts understand how seemingly disparate data sets might be Read more about CIA Can Anticipate Social Unrest ‘Three to Five Days’ Out in Some Cases[…]
In a paper [PDF] presented in August at the 25th Annual Usenix Security Symposium, researchers at École Polytechnique Fédérale de Lausanne, Cornell University, and The University of North Carolina at Chapel Hill showed that machine learning models can be stolen and that basic security measures don’t really mitigate attacks. Machine learning models may, for example, Read more about AI Machine-learning models vulnerable to reverse engineering[…]
Alexa will put up with just about anything. She has a remarkable tolerance for annoying behavior, and she certainly doesn’t care if you forget your please and thank yous. But while artificial intelligence technology can blow past such indignities, parents are still irked by their kids’ poor manners when interacting with Alexa, the assistant that Read more about Unintended consequences of AI: Amazon Echo seems to condition kids to be rude[…]
Until recently, the human species has been unable to take advantage of this fundamental biological technique, for we didn’t evolve the ability to swarm. Enter Unanimous A.I., a Silicon Valley startup founded in 2014 by serial entrepreneur and researcher Dr. Louis Rosenberg. The core question Rosenberg set out to answer was: Can humans swarm, and Read more about Swarm A.I. Correctly Predicts the Kentucky Derby, Accurately Picking all Four Horses of the Superfecta at 540 to 1 Odds – showing that humans can swarm[…]