Skip to main content

AI masters 49 Atari 2600 games without instructions




Artificial intelligence, machines and software with the ability to think for themselves, can be used for a variety of applications ranging from military technology to everyday services like automated telephone systems. However, none of the systems that currently exist exhibits learning abilities that would match the human intelligence. Recently, scientists have wondered whether an artificial agent could be given a tiny bit of human-like intelligence by modeling the algorithm on aspects of the primate neural system.

Using a bio-inspired system architecture, scientists have created a single algorithm that is actually able to develop problem-solving skills when presented with challenges that can stump some humans. And then they immediately put it to use learning a set of classic video games.

Scientists developed the novel agent (they called it the Deep Q-network), one that combined reinforcement learning with what's termed a "deep convolutional network," a layered system of artificial neural networks. Deep-Q is able to understand spatial relationships between different objects in an image, such as distance from one another, in such a sophisticated way that it can actually re-envision the scene from a different viewpoint. This type of system was inspired by early work done on the visual cortex.

Scientists considered tasks in which Deep-Q was able to interact with the environment through a sequence of observations, actions, and rewards, with an ultimate goal of interacting in a way to maximize reward. Reinforcement learning systems sound like a simple approach to developing artificial intelligence—after all, we have all seen that small children are able to learn from their mistakes. Yet when it comes to designing artificial intelligence, it is much trickier to ensure all the components necessary for this type of learning are actually included. As a result, artificial reinforcement learning systems are usually quite unstable.

Here, these scientists addressed previous instability issues in creating Deep-Q. One important mechanism that they specifically added to Deep-Q was “experience replay.” This element allows the system to store visual information about experiences and transitions much like our memory works. For example, if a small child leaves home to go to a playground, he will still remember what home looks like at the playground. If he is running and he trips over a tree root, he will remember that bad outcome and try to avoid tree roots in the future.

Using these abilities, Deep-Q is able to perform reinforcement learning, using rewards to continuously establish visual relationships between objects and actions within the convolution network. Over time, it identifies visual aspects of the environment that would promote good outcomes.

This bio-inspired approach is based on evidence that rewards during perceptual learning may influence the way images and sequences of events or resulting outcomes are processed within the primate visual cortex. Additionally, evidence suggests that in the mammalian brain, the hippocampus may actually support the physical realization of the processes involved in the “experience replay” algorithm.

Read More
Labels:

Comments

Post a Comment

Popular posts from this blog

Build Your Own Awesome Personal 3D Avatar with Avatara

Do you use social networks and want to build your own awesome 3D avatar? Maybe you want to send someone a cute cuddly image of yourself (kind of)? Or maybe you have your own ideas of what you would do with an Avatar… Well look no further than Avatara which I discovered from the MakeUseOf directory . You can create 3d avatars out of pre-set up templates or create your own from scratch. To start, visit Avatara’s homepage . You will see this screen: Click Get Started to umm, get started! That will take you to this screen: You see that you can build your own Avatar using an uploaded head shot like the Obama one above (just an example, guys). Or roll with one of their awesome avatars. I chose to start with a blank avatar by clicking Start with a blank avatar at the bottom of the screen. That takes you to here: I clicked on the filter at the top and told it to filter out everything but male characters and then I saw this: I rolled with Buck and continued. You need to click Select...
1 comment
Read more

Fun Tools to Translate Your Name into Japanese Calligraphy

Japanese calligraphy is an artistic writing style of the Japanese language. Its Chinese origins can be traced back to the twenty-eighth century BCE. Calligraphy found its way into Japanese culture in 600 CE and is known as the karayo tradition. For Westerners, calligraphy is forever fascinating. However, it takes years to learn how to properly draw the signs. Two basic principles must be known to understand Japanese writing: there are different writing styles and different alphabets. Kaisho for example, is a writing style most commonly used in print media. Tensho on the other hand is used in signatures. Other writing styles are Reisho, Gyosho and Sousho. The alphabets include Kanji, Hiragana, and Katakana. Katakana is used for writing foreign words. It can also serve to highlight words, in analogy to capital letters as we know them from the Roman / Latin alphabet (Romaji in Japanese). Each Kanji character has a meaning of its own, while Hiragana or Katakana characters merely repres...
Post a Comment
Read more

Boom, the startup that wants to build supersonic planes, just signed a massive deal with Virgin

Have you heard about Boom? Boom is a relatively new startup that’s aiming to build something pretty crazy. They’re not building an app… or a social network… or even some new gadget for the Kickstarter crowd. Boom wants to build planes. Really, really, really fast planes. Specifically, they’re trying to design and build a supersonic passenger plane that goes 2.2x the speed of sound. If all goes to plan, they’ll be able to shuttle people from New York to London in 3.5 hours, and SF to Tokyo in 4.5. Sound crazy? I wouldn’t disagree. It’s worth noting that the company is in the very early days for something as intensive, massive, and hugely expensive as designing and producing a passenger aircraft. They’re still working on their first prototype, and hope to fly it by late next year. But it’s also worth noting that the team behind the plane has some serious talent in its blood: the company’s 11 employees have collectively contributed to over 30 aircrafts — having worked on thin...
Post a Comment
Read more