Category Archives: IITBNF PR Team

A miniature, super-fast Silicon neuron could make brain-like chips

Brain-like electronic chips are a “holy grail” for computing technology. Recently, a team of Indian researchers has demonstrated an electronic neuron. It is 10x smaller and 1000x faster than biological neurons. A network of such neurons enables biology-like artificial intelligence (AI) in silicon chips. Such AI enables wide range of human-like tasks from ability to learn and then recognize patterns e.g. flowers, faces or even malignant tumors from benign ones.

Researchers around the world are engaged in the scientific pursuit to understand the human brain. Billions of interconnected neurons (the fundamental unit) enable parallel information processing in brain, outperforming today’s super computers. To put it in perspective, super computers take around million Watts of power, whereas a human brain consumes a mere 20 Watts of power to perform similar operations – thus biology a startling million fold more efficient than modern supercomputers!

Today, popular search engine softwares are able to recognize voice and images using traditional digital server farms that guzzle energy. The energy efficiency in biology partly lies in the neurons’ ability to code information in the timing of tiny “voltage spike” rather than digital “1” or ”0” expressed as large and small voltages. Following a unique approach leveraging on the existing fabrication technologies for mass produced high-speed chips, a team of researchers led by Prof. Udayan Ganguly in the Department of Electrical Engineering, IIT Bombay, devised an artificial neuron based on silicon-on-insulator(SOI) transistor technology.

The article published in Scientific Reports on 15th August, 2017 shows that the artificial neuron responds to stimulus akin to biology to produce electrical spikes – with a significant advantage of 10 times size reduction and 1000 times speed-up.

A network of such neurons is able to learn a range of classification tasks. Not only can it learn to classify different variant of Iris flower (Iris Sentosa, Iris Virginica, Iris Versicolor), but also classify malignant / benign cancers. “This study presents an essential stepping stone towards constructing energy efficient, bio-inspired machines that can learn to classify in diverse environments” remarks team member Prof. Nihar Ranjan Mohapatra, IIT Gandhinagar.

Graduate student Sangya Dutta works in the IIT Bombay Nano Fab, where she designs and tests these silicon neurons. Other team members, like graduate student Vinay Kumar design control circuits, and staff, Aditya Shukla, develops classification tests for the neural networks. Sangya explains “Conventional neurons use ions to conduct electricity and produce short “zaps” of current to represent “thoughts” i.e. information. We use electrons instead of 10,000 times heavier Sodium/Potassium ions to enable high-speed.” Inside the artificial neuronal device, a few electrons are driven by electric field to shoot out like bullets to break a tiny fraction of chemical bonds (one Si-Si bond in a billion) temporarily to generate a chain reaction, which delivers the signature neuronal “zap”. “The physics is beautiful!” remarks Prof. Udayan Ganguly.

The diverse team is partially funded by Nano-Mission, Department of Science and Technology to enable the break-through. Another stakeholder is Intel Corporation that has been supporting this breakthrough research under Intel India PhD Fellowship Program.

“These neurons leverage partially depleted Silicon-on-Insulator Technology, platform which is a commercial manufacturing technology,” opines Prof. Suman Datta, who directs a research center on Collective and Neuromorphic Computing at the University of Notre Dame, USA.

It is clear that leveraging a mature platform will support a large neural network – that will take hardware closer to the ultimate benchmark – the human brain with a 100-billion-neuron network.

Image_Neuron

References:

S. Dutta, V. Kumar, A. Shukla , N. R. Mohapatra, and U. Ganguly, “Leaky Integrate and Fire Neuron by Charge-Discharge Dynamics in Floating-Body MOSFET” Scientific Reports 2017, link

U. Ganguly, S. Dutta, V. Kumar “Leaky Integrate & Fire (LIF) Neuron based on Floating Body Effect” (Application No. 201721027169)

IIT Bombay and ISRO’s SCL indigenously augment their 180-nanometer Technology for versatile and powerful chips

A joint effort by IIT Bombay and ISRO’s Semi-Conductor Labs (SCL) Chandigarh has demonstrated, for the first time, indigenously developed Bipolar Junction Transistor to augment SCL’s 180-nanometer chip offering with versatile and powerful BiCMOS capability.  This success boosts SCL’s capability to serve the nation’s civilian & strategic for the new wave of Internet-of-Things (IoT) technologies.

Internet-of-Things (IoT) connects sensors & appliance to computers and the internet to make an intelligent system. Essentially, this network of system will “see” situations instantaneously (through sensors), make “smart decisions” (using the internet/ computer) and respond (with tool/ appliance) seamlessly. It requires many specialized integrated circuits (ICs) to create this network in different environments of national interest e.g. a home, hospital, factory or paddy field. For example, a sensor IC may measure (e.g. soil moisture or room temperature or blood oxygen level in a patient) and communicate to a controller IC to enable a response (e.g. optimal irrigation or energy-efficient air-conditioning or timely drug delivery respectively).  The sensors are normally “analog” as it reports a specific value of moisture/ temperature/ oxygen within a range – while this is converted into a simplified “digital” information in a computer for decision-making.  Thus such new age applications require versatile ICs capable of processing both analog and digital information (i.e. mixed signal). Bi-CMOS (short for Bipolar-CMOS) technology enables mixed signal ICs. It combines two transistor technologies in one chip – the high-speed and high power Bipolar Junction Transistor (BJT), and Low speed and low power Complementary Metal Oxide Semiconductor (CMOS). In simple terms, CMOS are equivalent of miniature on-off switches (i.e. digital) while BJTs are like miniature fan regulator dials (i.e. analog) that smoothly control the fan-speed. The result is a versatile technology platform in terms of integrated digital-analog (i.e. mixed) signal ICs, with optimal performance based on choice of high speed (BJT) and low power (CMOS), which strongly enables IoT applications.

India’s strategic needs is served by the 180-nanometer CMOS technology at Semi Conductor Labs Chandigarh.   A team from IIT Bombay lead by Prof. Udayan Ganguly has been collaborating with SCL to add BJT technology to the existing CMOS manufacturing baseline at SCL to indigenously develop BiCMOS technology. In May 2016, Dr. Piyush Bhatt, kick-started the project by developing process design for nano-fabrication based on existing SCL capabilities and demonstrating the technical feasibility through computer simulations. Next, the equivalent process was implemented in the IC fabrication lab by a team under Mr. H S. Jatana at SCL. In June 2017, the fabricated devices showed first signs of life! The device amplified the input signal a 100 times at the output! In fact, it worked so well that this amplification is sufficient for the first version of BiCMOS technology. Prof. Devang Khakhar, Director, IIT Bombay notes, “Such successful joint technology development attests to skill and the readiness of the Indian Agencies to indigenously enhance our capabilities – which is a first step towards market competitiveness in technology.”

India’s electronic consumption could outstrip its oil consumption by 2020 according to National Electronics Policy 2011. The Government of India is pushing mega-fabs (large-scale chip factories) to support this need. Shri Surinder Singh, Director, SCL has the enviable experience of already running a smaller but high-tech CMOS fab in India. “Mega-fabs are necessary but the ultimate goal is technology autonomy – enabled by indigenous technology development capability. Here, we have leveraged the world-class expertise of IIT Bombay to enable a manufacturable technology development at SCL. This collaborative model works!” remarks Singh. Strategic agencies have always needed to innovate around various international technology restrictions. An Indian semiconductor manufacturing enhanced with the ability for indigenous technology development significantly improves national access to technology that is custom, unique and secure focused on national needs & priorities.

Spurred on by the success, the team is working towards higher frequency BiCMOS technology. This involves further engineering to incorporate of new materials into the SCL fab using advanced processes. For example, replacing Silicon atoms with Germanium distorts the crystal and speed up electrons to enable 1000x faster systems. Such high-speed systems are used in high-end communications systems. Prof. Udayan Ganguly’s team works at the bustling Center of Excellence in Nanoelectronics (CEN) at IIT Bombay, which was seeded by the Ministry of Electronics and IT (MeitY) in 2005. Debashis Dutta, Group Coordinator, R&D in Electronics,  MeitY, says, “The research success of CEN at IIT Bombay is well known. However, the technology translation stories are coming out. I believe, these are signs of great things to come – which is essentially the realization of vision of our Ministry for Make in India in ESDM (Electronics Systems Design and Manufacturing)”.

bicmos_chips

Image: Versatile and powerful BiCMOS chips with integrated digital and analog information processing can enable new wave of Internet of Things applications for efficient & effective homes, healthcare, and agriculture for civic and strategic (image is representational)

Written by IITBNF PR team.