DeepMind adds memory to its AI system to tackle multiple Atari games

DeepMind adds memory to its AI system to tackle multiple Atari games

Many top research scientists have expressed concern in the past that fully autonomous AI could spell the end of human civilization as we know it. Just like humans, they don't always learn their lesson. This lets neural networks retain the pruned-down old skills, their version of hardened experience, without ballooning the size of that network to the point of uselessness.

Without an analogous system in place, even the smartest deep learning neural networks have trouble holding on to previous learning.

"Our algorithm specifically takes inspiration from [mammalian mechanisms] to address the problem of catastrophic forgetting".

With DeepMind's new AI learning capability, the firm just allowed a machine to emulate how humans collect information and then solve problems by using what it learned from its past experience. It's able to recall previously-learnt skills and apply them to new tasks.

Google continues to make moves on the AI front. In order to test the new AI, the DeepMind team set it to a number of Atari games back to back, with the special algorithm known as Elastic Weight Consolidation in hand. For a very long time, a goal of AI has been to replicate the way the human mind works, as demonstrated by neural networking and machine learning.

Their work was published February in the Proceedings of the National Academy of Sciences of the United States of America.

"We've hired 250 of the world's best scientists, so obviously they're here to let their creativity run riot, and we try and create an environment that's ideal for that", DeepMind CEO Demis Hassabis told the FT.

Neuroscience has been slowly revealing the mechanism of this sort of long-term pruning of inconsequential information, finding that synaptic pathways that are more critical to a task receive a sort of protection from being overwritten in the future.

"The greed motivation reflects the temptation to take out a rival and collect all the apples oneself."

While this may not sound particularly impressive, it represents a major step forward for AI and brings us one step closer to the holy grail/terrifying existential threat of artificial general intelligence (AGI), sometimes referred to as strong AI. When eventually we get there, it will raise a host of ethical and safety concerns that will need to be carefully addressed.

The truly exciting possibilities begin there, when scientists can begin to really start designing out-there experiments to perform on human brains - because, for the most part, a real human brain won't be necessary at all.

Google's efforts to develop more advanced AI technologies through its company DeepMind are attracting attention.

Since 2014, DeepMind has been playing Atari video games. It was the first time than an AI technology beat an expert level human GO player.

Related News: