IBM chips mimic brain like functionality

1 min read

IBM researchers have unveiled two new experimental computer chips that emulate the brain's abilities for perception, action and cognition.

The chips are a result of a six year, $41million cognitive computing initiative, dubbed SyNAPSE, which hopes to realise a system that not only analyses complex information from multiple sensory modalities at once, but also dynamically rewires itself as it interacts with its environment – all while rivaling the brain's compact size and low power usage. "Systems built with these chips won't be programmed the same way traditional computers are today," said lead researcher Dharmendra Modha. "Rather, cognitive computers are expected to learn through experiences, find correlations, create hypotheses, remember and learn from the outcomes, mimicking the brains structural and synaptic plasticity." The prototype chips demonstrated by Modha and his team 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). Both cores were fabricated in 45nm SOI-CMOS and contain 256 neurons. One of the cores contains 262,144 programmable synapses, while the other features 65,536 learning synapses. The IBM team has successfully demonstrated simple applications like navigation, machine vision, pattern recognition, associative memory and classification. The company's overarching cognitive computing architecture is an on chip network of lightweight cores, creating a single integrated system of hardware and software. Its long term goal is to build a chip system with ten billion neurons and a hundred trillion synapses, while consuming 1kw of power and occupying less than 2l of volume. Modha concluded: "This architecture represents a critical shift away 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."