Lyrebird will offer an API to copy the voice of anyone. It will need as little as one minute of audio recording of a speaker to compute a unique key defining her/his voice. This key will then allow to generate anything from its corresponding voice. The API will be robust enough to learn from noisy recordings. The following sample illustrates this feature, the samples are not cherry-picked.
Please note that those are artificial voices and they do not convey the opinions of Donald Trump, Barack Obama and Hillary Clinton.
Self-taught artificial intelligence beats doctors at predicting heart attacks
In the new study, Weng and his colleagues compared use of the ACC/AHA guidelines with four machine-learning algorithms: random forest, logistic regression, gradient boosting, and neural networks. All four techniques analyze lots of data in order to come up with predictive tools without any human instruction. In this case, the data came from the electronic medical records of 378,256 patients in the United Kingdom. The goal was to find patterns in the records that were associated with cardiovascular events.
First, the artificial intelligence (AI) algorithms had to train themselves. They used about 78% of the data—some 295,267 records—to search for patterns and build their own internal “guidelines.” They then tested themselves on the remaining records. Using record data available in 2005, they predicted which patients would have their first cardiovascular event over the next 10 years, and checked the guesses against the 2015 records. Unlike the ACC/AHA guidelines, the machine-learning methods were allowed to take into account 22 more data points, including ethnicity, arthritis, and kidney disease.
All four AI methods performed significantly better than the ACC/AHA guidelines. Using a statistic called AUC (in which a score of 1.0 signifies 100% accuracy), the ACC/AHA guidelines hit 0.728. The four new methods ranged from 0.745 to 0.764, Weng’s team reports this month in PLOS ONE. The best one—neural networks—correctly predicted 7.6% more events than the ACC/AHA method, and it raised 1.6% fewer false alarms. In the test sample of about 83,000 records, that amounts to 355 additional patients whose lives could have been saved. That’s because prediction often leads to prevention, Weng says, through cholesterol-lowering medication or changes in diet.
We’ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.
Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games
Real-world artificial intelligence (AI) applications often require multiple agents to work in a collaborative effort. Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI. In this paper, we take StarCraft combat game as the test scenario, where the task is to coordinate multiple agents as a team to defeat their enemies. To maintain a scalable yet effective communication protocol, we introduce a multiagent bidirectionally-coordinated network (BiCNet [‘bIknet]) with a vectorised extension of actor-critic formulation. We show that BiCNet can handle different types of combats under diverse terrains with arbitrary numbers of AI agents for both sides. Our analysis demonstrates that without any supervisions such as human demonstrations or labelled data, BiCNet could learn various types of coordination strategies that is similar to these of experienced game players. Moreover, BiCNet is easily adaptable to the tasks with heterogeneous agents. In our experiments, we evaluate our approach against multiple baselines under different scenarios; it shows state-of-the-art performance, and possesses potential values for large-scale real-world applications.
Enabling Continual Learning in Neural Networks
Deep neural networks are currently the most successful machine learning technique for solving a variety of tasks including language translation, image classification and image generation. However, they have typically been designed to learn multiple tasks only if the data is presented all at once. As a network trains on a particular task its parameters are adapted to solve the task. When a new task is introduced, new adaptations overwrite the knowledge that the neural network had previously acquired. This phenomenon is known in cognitive science as ‘catastrophic forgetting’, and is considered one of the fundamental limitations of neural networks.
[…]
A neural network consists of several connections in much the same way as a brain. After learning a task, we compute how important each connection is to that task. When we learn a new task, each connection is protected from modification by an amount proportional to its importance to the old tasks. Thus it is possible to learn the new task without overwriting what has been learnt in the previous task and without incurring a significant computational cost. In mathematical terms, we can think of the protection we attach to each connection in a new task as being linked to the old protection value by a spring, whose stiffness is proportional to the connection’s importance. For this reason, we called our algorithm Elastic Weight Consolidation (EWC).
Google just showed off a new Video Intelligence API that lets you search for objects within video clips, here’s an bit of the demo pic.twitter.com/wOPwsmnAfe
— Karissa Bell (@karissabe)March 8, 2017
edit: API announcement is here
Beating the World’s Best at Super Smash Bros. with Deep Reinforcement Learning
There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of RL tasks, from Atari games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning, that learn to play from experience with minimal knowledge of the specific domain of interest. In this work, we will investigate the performance of these methods on Super Smash Bros. Melee (SSBM), a popular console fighting game. The SSBM environment has complex dynamics and partial observability, making it challenging for human and machine alike. The multi-player aspect poses an additional challenge, as the vast majority of recent advances in RL have focused on single-agent environments. Nonetheless, we will show that it is possible to train agents that are competitive against and even surpass human professionals, a new result for the multi-player video game setting.
Think about the last post you liked — it most likely involved a photo or video. But, until recently, online search has always been a text-driven technology, even when searching through images. Whether an image was discoverable was dependent on whether it was sufficiently tagged or had the right caption — until now.
That’s changing because we’ve [Facebook] pushed computer vision to the next stage with the goal of understanding images at the pixel level. This helps our systems do things like recognize what’s in an image, what type of scene it is, if it’s a well-known landmark, and so on. This, in turn, helps us better describe photos for the visually impaired and provide better search results for posts with images and videos.
Wearable AI system can detect a conversation’s tone
It’s a fact of nature that a single conversation can be interpreted in very different ways. For people with anxiety or conditions such as Asperger’s, this can make social situations extremely stressful. But what if there was a more objective way to measure and understand our interactions?
Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Institute of Medical Engineering and Science (IMES) say that they’ve gotten closer to a potential solution: an artificially intelligent, wearable system that can predict if a conversation is happy, sad, or neutral based on a person’s speech patterns and vitals.
AI Decisively Defeats Human Poker Players
Humanity has finally folded under the relentless pressure of an artificial intelligence named Libratus in a historic poker tournament loss. As poker pro Jason Les played his last hand and leaned back from the computer screen, he ventured a half-hearted joke about the anticlimactic ending and the lack of sparklers. Then he paused in a moment of reflection.
“120,000 hands of that,” Les said. “Jesus.”
Libratus lived up to its “balanced but forceful” Latin name by becoming the first AI to beat professional poker players at heads-up, no-limit Texas Hold'em. The tournament was held at the Rivers Casino in Pittsburgh from 11-30 January. Developed by Carnegie Mellon University, the AI won the “Brains Vs. Artificial Intelligence” tournament against four poker pros by $1,766,250 in chips over 120,000 hands (games). Researchers can now say that the victory margin was large enough to count as a statistically significant win, meaning that they could be at least 99.7 percent sure that the AI victory was not due to chance.
One approach to push the codification of what human hackers do, is to take
the hackers out of the equation. This is precisely what the DARPA Cyber Grand Challenge was set out to do.The DARPA Cyber Grand Challenge (CGC) was designed as a Capture The Flag (CTF) competition among autonomous systems without any humans being involved. During the competition, Cyber Reasoning Systems (CRSs) would find vulnerabilities in binaries, exploit them, and generate patches to protect them from attacks, without any human involvement at all.
The separation between human and machine is key, as it forces the participants to codify, in algorithms, the techniques used for both attack and defense. Although the competition was only a first step toward capturing the art of hacking, it was an important one: for the first time, completely autonomous systems were hacking one another with code, and not human intuition, driving the discovery of flaws in complex software systems.
DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
Artificial intelligence has seen a number of breakthroughs in recent years, with games often serving as significant milestones. A common feature of games with these successes is that they involve information symmetry among the players, where all players have identical information. This property of perfect information, though, is far more common in games than in real-world problems. Poker is the quintessential game of imperfect information, and it has been a longstanding challenge problem in artificial intelligence. In this paper we introduce DeepStack, a new algorithm for imperfect information settings such as poker. It combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition about arbitrary poker situations that is automatically learned from self-play games using deep learning. In a study involving dozens of participants and 44,000 hands of poker, DeepStack becomes the first computer program to beat professional poker players in heads-up no-limit Texas hold'em. Furthermore, we show this approach dramatically reduces worst-case exploitability compared to the abstraction paradigm that has been favored for over a decade.
my g-g-g-glorious thoughts hacker
kreuzaderny