Cognitive computer

A cognitive computer combines artificial intelligence and machine-learning algorithms, in an approach which attempts to reproduce the behavior of the human brain. [1]

An example of neural network implementations of cognitive convolution and deep learning is provided by the IBM company’s Watson machine. A subsequent development by IBM is the true microchip architecture, which is designed to be closer to the human brain than the Neumann architecture . [1] In 2017 Intel announced its own version of a cognitive chip in “Loihi”, which will be available to university and research labs in 2018.

Intel Loihi chip

Main article: Intel Loihi

Intel’s self-learning neuromorphic chip, named Loihi, perhaps named after the Hawaiian seamount Loihi , offers substantial power efficiency designed after the human brain. Intel claims Loihi is about 1000 times more energy efficient than the general-purpose computing power needed to train the neural networks that rival Loihi’s performance. In theory, this would be both a machine learning tool and a neural networks (CNNs) or deep learning neural networks. Intel points to a system for monitoring a person’s heartbeat, taking readings after events such as exercise or eating, and uses cognitive computing to normalize the data and work out the ‘normal’ heartbeat. It can then place abnormalities, but also deal with any new events or conditions.

The first iteration of the Loihi chip was made using Intel’s 14 nm manufacturing process, and houses 1,024 artificial neurons that provide 130,000 simulated neurons each. This offers 130 million synapses, which is still rather than 80 billion synapses, and behind IBM’s TrueNorth , which has around 16 billion by using 64 by 4,096 cores. [2]

IBM TrueNorth Chip

Main article: TrueNorth

The IBM cognitive computers implementing learning using Hebbian theory . Instead of being white in a traditional sense programmable Within machine language Gold Higher Level programming language Such a device learns by Inputting bodies through an input device That are aggregated computational Within a convolution or neural network architecture consistant en weights Within a parallel memory system. An early instantiation of such a device has been developed under the Darpa SyNAPSE program at IBM by Dharmendra Modha . [ quote needed ]

In 2017 this IBM 64-chip array will contain the equivalent processing of 64 million neurons and 16 billion synapses, yet absolutely sips energy – each processor consumes just 10 watts of electricity. Like other neural networks, this system will be used in the field of recognition and sensory processing roles. The Air Force wants to combine the TrueNorth ability to convert multiple data feeds – whether it ‘s audio, video or text – into a machine with a conventional machine. This is not the first time that IBM’s neural chip system has been integrated into cutting-edge technology. August, 2017 Samsung Dynamic Vision Sensors enabling cameras to capture images at up to 2,000 fps while burning through just 300 milliwatts of power.

Criticism

There are many approaches and definitions for a cognitive computer , [3] and other approaches may be more fruitful. [4]

See also

  • Cognitive computing
  • AI accelerator
  • Synapse

References

  1. ^ Jump up to: a b Dharmendra Modha (interview), “A computer that thinks,” New Scientist 8 November 2014, Pages 28-29
  2. Jump up^ “Intel unveils Loihi neuromorphic chip, chases IBM in artificial brains”. October 17, 2017. AITrends.com
  3. Jump up^ Schank, Roger C.; Childers, Peter G. (1984). The cognitive computer: on language, learning, and artificial intelligence . Addison-Wesley Pub. Co. ISBN 9780201064438.
  4. Jump up^ Wilson, Stephen (1988). “The Cognitive Computer: On Language, Learning, and Artificial Intelligence by Roger C. Schank, Peter Childers (review)”. Leonardo . 21 (2): 210. ISSN 1530-9282. Retrieved 13 January 2017.

Leave a Reply

Your email address will not be published. Required fields are marked *

Copyright computerforum.eu 2018
Shale theme by Siteturner