Tag: Ladder (page 1 of 2)

The Class-Domination Theory of Power

May 9, 2015 / / 0 Comments

by G. William DomhoffNOTE: WhoRulesAmerica.net is largely based on my book,Who Rules America?, first published in 1967 and now in its7th edition. This on-line document is presented as a summary of some of the main ideas in that book.Who has predominant power in the United States? The short answer, from 1776 to the present, is: Those who have the money -- or more specifically, who own income-producing land and businesses -- have the power. George Washington was one of the biggest landowner [...]

View Article Here Read More

Is playing ‘Space Invaders’ a milestone in artificial intelligence?

February 25, 2015 / / 0 Comments





Excerpt from latimes.com

Computers have beaten humans at chess and "Jeopardy!," and now they can master old Atari games such as "Space Invaders" or "Breakout" without knowing anything about their rules or strategies.

Playing Atari 2600 games from the 1980s may seem a bit "Back to the Future," but researchers with Google's DeepMind project say they have taken a small but crucial step toward a general learning machine that can mimic the way human brains learn from new experience.

Unlike the Watson and Deep Blue computers that beat "Jeopardy!" and chess champions with intensive programming specific to those games, the Deep-Q Network built its winning strategies from keystrokes up, through trial and error and constant reprocessing of feedback to find winning strategies.

Image result for space invaders

“The ultimate goal is to build smart, general-purpose [learning] machines. We’re many decades off from doing that," said artificial intelligence researcher Demis Hassabis, coauthor of the study published online Wednesday in the journal Nature. "But I do think this is the first significant rung of the ladder that we’re on." 
The Deep-Q Network computer, developed by the London-based Google DeepMind, played 49 old-school Atari games, scoring "at or better than human level," on 29 of them, according to the study.
The algorithm approach, based loosely on the architecture of human neural networks, could eventually be applied to any complex and multidimensional task requiring a series of decisions, according to the researchers. 

The algorithms employed in this type of machine learning depart strongly from approaches that rely on a computer's ability to weigh stunning amounts of inputs and outcomes and choose programmed models to "explain" the data. Those approaches, known as supervised learning, required artful tailoring of algorithms around specific problems, such as a chess game.

The computer instead relies on random exploration of keystrokes bolstered by human-like reinforcement learning, where a reward essentially takes the place of such supervision.
“In supervised learning, there’s a teacher that says what the right answer was," said study coauthor David Silver. "In reinforcement learning, there is no teacher. No one says what the right action was, and the system needs to discover by trial and error what the correct action or sequence of actions was that led to the best possible desired outcome.”

The computer "learned" over the course of several weeks of training, in hundreds of trials, based only on the video pixels of the game -- the equivalent of a human looking at screens and manipulating a cursor without reading any instructions, according to the study.

Over the course of that training, the computer built up progressively more abstract representations of the data in ways similar to human neural networks, according to the study.
There was nothing about the learning algorithms, however, that was specific to Atari, or to video games for that matter, the researchers said.
The computer eventually figured out such insider gaming strategies as carving a tunnel through the bricks in "Breakout" to reach the back of the wall. And it found a few tricks that were unknown to the programmers, such as keeping a submarine hovering just below the surface of the ocean in "Seaquest."

The computer's limits, however, became evident in the games at which it failed, sometimes spectacularly. It was miserable at "Montezuma's Revenge," and performed nearly as poorly at "Ms. Pac-Man." That's because those games also require more sophisticated exploration, planning and complex route-finding, said coauthor Volodymyr Mnih.

And though the computer may be able to match the video-gaming proficiency of a 1980s teenager, its overall "intelligence" hardly reaches that of a pre-verbal toddler. It cannot build conceptual or abstract knowledge, doesn't find novel solutions and can get stuck trying to exploit its accumulated knowledge rather than abandoning it and resort to random exploration, as humans do. 

“It’s mastering and understanding the construction of these games, but we wouldn’t say yet that it’s building conceptual knowledge, or abstract knowledge," said Hassabis.

The researchers chose the Atari 2600 platform in part because it offered an engineering sweet spot -- not too easy and not too hard. They plan to move into the 1990s, toward 3-D games involving complex environments, such as the "Grand Theft Auto" franchise. That milestone could come within five years, said Hassabis.

“With a few tweaks, it should be able to drive a real car,” Hassabis said.

DeepMind was formed in 2010 by Hassabis, Shane Legg and Mustafa Suleyman, and received funding from Tesla Motors' Elon Musk and Facebook investor Peter Thiel, among others. It was purchased by Google last year, for a reported $650 million. 

Hassabis, a chess prodigy and game designer, met Legg, an algorithm specialist, while studying at the Gatsby Computational Neuroscience Unit at University College, London. Suleyman, an entrepreneur who dropped out of Oxford University, is a partner in Reos, a conflict-resolution consulting group.

View Article Here Read More

The Mystery of the Ghost Ship Lunatic

January 27, 2015 / / 0 Comments

The Lunatic Piran found abandoned Jure Stwerk at the Helm           ...

View Article Here Read More

Heavenletter #4180 A Whole New World, May 5, 2012

May 5, 2012 / / 0 Comments

{mainvote}

God said:

From My heart to yours emanates My love in full splendor. What else could I possibly give to you but what I AM? I say that even as I realize that sometimes, in times of woe, you can only think I give you what you perceiv...

View Article Here Read More

Heavenletter #4152 Oneness Rising, April 7, 2012

April 7, 2012 / / 0 Comments

{mainvote}

God said:

When your cup runneth over, enjoy it. You are meant for brimful. A cup empties only so that it may be filled. You are ascending to love. Ascension does not have to be something that happens to you. Rise to it. Rise close...

View Article Here Read More

Heavenletter #4129 Start Moving. Meet the Horizon., March 15, 2012

March 15, 2012 / / 0 Comments

{mainvote}

God said:

Of course, from your perception, you are always right. Right or not right is not the question. The question is not your virtue. The question is: Where do you go from here?

Everyone thinks he or she is right. Both par...

View Article Here Read More

SaLuSa 6-February-2012

February 6, 2012 / / 0 Comments

{mainvote}

Naturally we need to be aware of what Michael is doing, and have been following the events associated with the trip to Neptune. What we must however stress is that we have our own responsibilities, and would never interfere with the m...

View Article Here Read More

HEAVEN #3966 God Says Now, October 4, 2011

October 4, 2011 / / 0 Comments

{mainvote}

God said:

I hold a cup to your lips, and I say, "Drink from this cup," Yet you are busy on other matters. Take a moment. Sit near Me, and drink from the cup I offer you. This is a wonderful time We will have. Sit knee to...

View Article Here Read More

HEAVEN #3958 Believe in God, September 26, 2011

September 26, 2011 / / 0 Comments

{mainvote}

God said:

On a cloudy day, life goes on just the same. As for you, My darlings, when skies seem dark for you, don't let the clouds dim your view. Keep on going just the same.

In life in the world, nothing has happened. You...

View Article Here Read More

Birthing a Better Future

July 14, 2011 / / 0 Comments

{mainvote}

a message from Gillian MacBeth-Louthan

Wednesday, 13 July, 2011  

You each walk into a stairway of questing, of questioning, of asking, what is the next step of my journey, of my mission? You stand at the top of the stair...

View Article Here Read More

Adama: Invitation to Come to Telos

May 29, 2011 / / 0 Comments

{mainvote}

Posted on May 28, 2011 by soulinsightawakenings Note: Usually I post things from Adama on my blog, ConversationsWithAdama.wordpress.com – but today he insisted that this (http://soulinsightawakenings.wordpress.com/2011/05/28/ada...

View Article Here Read More

Co-Conscious Creators

May 25, 2011 / / 0 Comments

{mainvote}

Communiques is a channeled message from the One Mind and the One Thought, the only conscious that is the One. We would wish to be seen as you speaking to yourself. It is our hope and our intent that our words inspire and awaken that i...

View Article Here Read More

11:11 Master Numbers!

September 16, 2006 / / 0 Comments

Created, Channeled, Written, Published and copyrighted by Gillian

MacBeth-Louthan

IN THIS ISSUE

-11:11 LIVING LIGHT CONCORDANCE Asheville NC

-ELEVEN IS THE NUMBER OF LIGHT

-ENTER THE SOLAR CROSSINGS OF YOUR LIGHT

View Article Here Read More
Older posts

Deep Space Leaderboard 728x90

Creative Commons License
This work is licensed under a
Creative Commons Attribution 4.0
International License.
unless otherwise marked.

Terms of Use | Privacy Policy



— Up ↑ —