Solving Atari games with Distributed Reinforcement Learning

Solving #Atari games with distributed reinforcement learning. #MachineLearning

  • One particular step towards achieving this ideal was distributing a state-of-the-art Reinforcement Learning algorithm on a large CPU cluster, allowing super-fast training of agents that learned to master a wide range of Atari 2600 games.
  • The A3C algorithm developed later was able to achieve human performance in most games and did so with a similar amount of training time.
  • By distributing the BA3C (details of single-machine implementation here) reinforcement learning algorithm, we were able to make an agent teach itself to play a wide range of Atari games rapidly, by just looking at a raw pixel output (game screen) from the game emulator.
  • In the game of Breakout, our agent achieves a superhuman score in just 20 minutes, which is a significant reduction of the single machine implementation learning time.
  • The development of a distributed evolution strategy (ES) algorithm has led researchers from OpenAI to train agents to play Atari games in one hour by using 720 parallel CPUs.

We present the result of research conducted at deepsense.ai, that focuses on distributing a reinforcement learning algorithm to train on a large CPU cluster
Continue reading “Solving Atari games with Distributed Reinforcement Learning”

IBM and MIT partner on artificial intelligence research

IBM and MIT partner on artificial intelligence research

  • BOSTON (AP) — IBM is planning to spend $240 million over the next decade to create an artificial intelligence research lab at MIT.
  • Massachusetts Institute of Technology on Thursday announced the formation of the new MIT-IBM Watson AI Lab.
  • It will support joint research by IBM and MIT scientists.
  • Its mission will include advancing the hardware, software and algorithms used for artificial intelligence.

BOSTON (AP) — IBM is planning to spend $240 million over the next decade to create an artificial intelligence research lab at MIT.
Massachusetts Institute of Technology on Thursday announced the formation of the new MIT-IBM Watson AI Lab. It will support joint research by IBM and MIT scientists.
Its mission will include advancing the hardware, software and algorithms used for artificial intelligence. It also will tackle some of the economic and ethical implications of intelligent machines and look at its commercial application for industries ranging from health care to cybersecurity.
Continue reading “IBM and MIT partner on artificial intelligence research”

What is Artificial Intelligence?

What is Artificial Intelligence? 
  [via @Accenture]
#AI #ML #DL #NLP #Robots
@ipfconline1

  • In this series, I will try to provide an overview of what constitutes AI, how it is already being applied to banking, insurance and capital markets today, and how organizations can craft a value-driven AI strategy.
  • We view AI as a collection of multiple technologies that enable machines to sense, comprehend and act—and learn—either on their own or to augment human activities.
  • And unlike conventional capital, thanks to its self-learning capabilities, AI can actually improve over time.
  • Today’s definition of AI refers to multiple technologies that can be combined in different ways to:

    All three capabilities are underpinned by the ability to learn from experience and adapt over time.

  • To learn more, take a look at Accenture’s Top 5 Technology Trends 2017, and at how we envision AI to change the Future of Business.

The pace of change in digital technology is accelerating exponentially, particularly in the field of artificial intelligence (AI). All major technology companies are reorganizing around this red-hot sector, and it dominated discussions and presentations at the recent World Economic Forum 2017 in Davos. In this series, I will try to provide an overview of what constitutes AI, how it is already being applied to banking, insurance and capital markets today, and how organizations can craft a value-driven AI strategy.
Continue reading “What is Artificial Intelligence?”

BBC

Garry Kasparov: Why the world should embrace AI  #ai

  • Not at all, says chess grandmaster and former World Chess Champion Garry Kasparov.
  • Kasparov has direct experience of being humbled by a machine, so it’s perhaps surprising that he has a pro-AI outlook.
  • Since then Kasparov has gone on to become something of an AI authority: his new book, Deep Thinking: Where Machine Intelligence Ends and Human Creativity Begins was released last month.
  • The BBC Click team caught up with Kasparov at this year’s Hay Festival in the UK.
  • In the video above, watch what he had to say about the inevitability of AI’s rise – and why it could actually be a revolution that will help humans work even better.

The chess grandmaster, who once saw his skills outstripped by artificial intelligence, explains why it’s time to welcome the era of smart machines.
Continue reading “BBC”

Cars are learning to hear like humans and self-diagnose problems

Hear that? Your #car just did - ! 🚗 #iot #ai

  • Just like humans identify whether or not there is a problem with the car by hearing odd sounds coming from the engine or by hearing creaking sounds, cars can identify as well.
  • Their software can give cars the ability to diagnose problems themselves by simply hearing anomalous sounds coming from the car and/or the environment.
  • They are testing the tech by providing it with many sounds that come from their cars.
  • This can be a huge boost as one of the important factors of customer dissatisfaction is odd noises coming from a car and not being able to locate the problem.
  • Other than diagnosing problems, this tech can also be used to help cars in perceiving their environment.

Intelligent machines are not only trying to learn and act like humans, they are beginning to sense their environment like them as well. Latest among them are cars that are getting a sense of hearing that would allow them to enhance their intelligence level by perceiving their environment like humans do.
Continue reading “Cars are learning to hear like humans and self-diagnose problems”

Learning to Love Artificial Intelligence

Learning to Love Artificial Intelligence: An #AI blog by @Informatica #CIO @e_graeme

  • To prove this, the experimenters asked the doctors to teach a group software developers how to spot cancer in an MRI image.
  • Of course, you could point out that doctors’ jobs could be put at risk by the rise of intelligent machines — and you would be right.
  • In the future, we may discover that the best and highest value use for humans won’t be in doing repetitive tasks like driving trucks or “practicing” medicine, but in teaching machines how to do them so humans are freed up to innovate.
  • Do a quick Google search and you will see a multitude of stories on how AI and intelligent machines are replacing human (educated) guesswork with super-human precision.
  • So instead of worrying about the threat of Artificial Intelligence, let’s look forward to a more prosperous future created by the amazing things AI makes possible.

Learning to Love Artificial Intelligence
Continue reading “Learning to Love Artificial Intelligence”

Rise of artificial intelligence: learning to love machines

yes Yes YES
@Kasparov63, who knows a thing or two about being challenged by tech progress:

  • To use this website, cookies must be enabled in your browser.
  • To enable cookies, follow the instructions for your browser below.
  • There is a specific issue with the Facebook in-app browser intermittently making requests to websites without cookies that had previously been set.
  • This appears to be a defect in the browser which should be addressed soon.
  • The simplest approach to avoid this problem is to continue to use the Facebook app but not use the in-app browser.

It was my blessing and my curse to be the world chess champion when computers finally reached a world championship level of play. When I resigned the final match game against the IBM supercomputer Deep Blue on May 11, 1997, I became the first world champion to be defeated in a classical match by a machine.
Continue reading “Rise of artificial intelligence: learning to love machines”