An Indian techie Dharmendra Modha is leading an initiative at IBM to develop a chip (microprocessor) that mimics the functioning of the human brain.
Describing the new microprocessor as cognitive computing chips, IBM researchers say they will emulate the brain’s abilities for perception, action and cognition.
An experimental version of the chip has already been developed.
The first two prototype chips were recently fabricated at IBM’s chip-making facility in Fishkill, N.Y. and are undergoing testing at the company’s research labs in Yorktown Heights, N.Y. and San Jose, California.
A key feature of the new chips is that they could consume several orders of magnitude less power and
space than the current generation of computers.
This means more powerful computers in smaller form-factors since you can cram more chips in the same amount of space without the vexing problem of overheating.
Departing from traditional concepts in designing and building computers, IBM’s so called neurosynaptic computing chips replicate the behavior between spiking neurons and synapses in the brain through advanced algorithms and silicon circuitry.
Systems built with these chips are called cognitive computers and won’t be programmed the same way computers are today. No more sweating, smelling H1B/L1 desis landing in Amreeka? Thank you, God! 😉
Instead, cognitive computers will learn through experiences, find correlations, create hypotheses, and remember – and learn from – the outcomes, mimicking the brains structural and synaptic plasticity.
IBM researchers are combining principles from nanoscience, neuroscience and supercomputing as part of a multi-year cognitive computing initiative. The company and its university collaborators have won $21 million in funding from the Defense Advanced Research Projects Agency (DARPA) for Phase 2 of the Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) project.
SyNAPSE’s goal is to build a system that not only analyzes complex information from multiple sensory modalities simultaneously but also dynamically rewires itself as it interacts with its environment – all while rivaling the brain’s compact size and low power usage.
IBM’s team has successfully completed Phases 0 and 1.
Dharmendra Modha, a project leader for IBM Research at Alamaden (California) and an IIT-Bombay alumnus, said:
This is a major initiative to move beyond the von Neumann paradigm that has been ruling computer architecture for more than half a century. Future applications of computing will increasingly demand functionality that is not efficiently delivered by the traditional architecture. These chips are another significant step in the evolution of computers from calculators to learning systems, signaling the beginning of a new generation of computers and their applications in business, science and government.
IBM’s first cognitive computing prototype chips contain no biological elements but use digital silicon circuits inspired by neurobiology to make up what is referred to as a “neurosynaptic core” with integrated memory (replicated synapses), computation (replicated neurons) and communication (replicated axons).
IBM has built two working prototype designs.
Both cores were fabricated in 45 nm SOI-CMOS and contain 256 neurons. One core contains 262,144 programmable synapses and the other contains 65,536 learning synapses.
Modha’s team at IBM has demonstrated simple applications like navigation, machine vision, pattern recognition, associative memory and classification.
IBM’s overarching cognitive computing architecture is an on-chip network of light-weight cores, creating a single integrated system of hardware and software. This architecture marks a shift from traditional von Neumann computing to a potentially more power-efficient architecture that has no set programming, integrates memory with processor and mimics the brain’s event-driven, distributed and parallel processing.
IBM’s long-term goal is to build a chip system with ten billion neurons and hundred trillion synapses, while consuming merely one kilowatt of power and occupying less than two liters of volume.