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.

IIT Bombay Nanofabrication Facility: Key to the Future

About two years ago, we were asked to contribute a chapter to the ICT (Information and Communication Technology) ‘Vision-2035’ document that TIFAC (Technology Information Forecasting and Assessment Council under the Department of Science and Technology) was going to come out with – crystal-gazing twenty years into the future to predict the shape and impact of ICT then, with special emphasis on India. Our chapter, in particular, was to forecast the trajectory of solid-state technology. After several iterations, we decided that the best way to present this was as a vision, of how ICT would enable essential aspects of Indian lives, and then link that to the role that solid-state technology would have to play therein.

Now, as we get ready to kick off a new website for IITBNF (IIT Bombay Nanofabrication Facility), we thought that the inaugural blog entry could reference that vision by way of defining the broad collective aspiration of the IITBNF member community. So, here it is…

We envision transformative impact of future advances in solid-state technology on India and its people. At the center of this vision is our core idea of empowerment. The vision is such:

A child in a remote village will have access to information and learning tools at the same extent as in a contemporary smart city. These would be the means of cultivating the minds of the future Indian citizenry.

To this end, we imagine that every child in every village will have access to world-class education, in ‘virtual reality’ classrooms enabled by the technological capability to collect, process, and transmit enormous amounts of interface and sensor data – all in real time, and with unbelievable energy-efficiency. The same technologies would enable highly interactive access to best-in-class healthcare consultation, and possibly remote treatment, to every Indian. They would also enable Indian farmers to get real-time agricultural inputs, e.g. irrigation quantity and timing, based on extensive and accurate sensor network data on soil and environmental parameters. All this would be powered by making every village in India energy-surplus – by locally generating and using energy with utmost efficiency (and cleanliness, i.e. with minimal environmental impact). Thus, we envisage that by 2035, solid-state technology will be instrumental in providing what we would call today a ‘first-world quality of life’ to all Indians, rural and urban. There are, of course, significant challenges to overcome before we reach there. We fully expect that these will be successfully overcome.

To what we had written then, we add our hope now that IITBNF will play a substantial role in surmounting some of these challenges by coming out with societally-relevant innovations in solid-state technology. In what follows, we zoom in from ICT in general to solid-state technology in particular – its past, present and (predicted) future evolution, as we had outlined it in the Vision-2035 document.

ICT has been driven by rapid developments in solid-state (or semiconductor) device technology – captured, in the context of information processing (logic devices), by the iconic Moore’s Law. This broad area has also driven development in the critical field of energy – specifically in solar photovoltaics for generation and batteries for storage. Solid-state devices have found applications in various fields like computing, communication, sensing and actuating, human-interfacing and energy conversion.

The present ICT revolution started as a convergence of computing and communication, combined with elementary human-interfacing, in the form of networked computers. Today’s tablet computers and smartphones incorporate, in addition, hitherto unimaginable amounts of sensing (proximity, acceleration, ambient lighting, sound…) and advanced human-interfacing (voice commands and readout, proximity-based display, elementary haptics). As such, they presage the coming era of total convergence.

Over the next twenty years, we envisage that humans will design around themselves real and virtual ‘intelligent environments’; that ICT will be built into every element of such built environments; and that it will feature seamless integration of computing, communication, sensing/actuation, human-interfacing and energy conversion devices. These ubiquitous and interconnected sensors, actuators, displays and interface devices will naturally generate huge amounts of data to be processed and communicated. For the sake of sustainability, such integration would need to be performed with utmost energy efficiency and environment neutrality.

As is probably known to most of you, R&D at IITBNF encompasses nearly all areas of solid-state device technology. We invite students and faculty (at IIT Bombay and elsewhere), members of industry and government, to partner with us in the journey of discovery that lies ahead of us.

In the coming months and years, members of the IITBNF community will use this blog to reach out to you with thoughts, opinions, sorrows and joys. We look forward to your continued feedback.

About the Authors:

Swaroop Ganguly is an Associate Professor at the Department of Electrical Engineering at IIT-Bombay and an active member of the IITBNF community. His research interests revolve around the physics of nanoelectronic devices and he likes to teach physics to electrical engineering students. He spends too much time on issues pertaining to the IITB Nanofabrication Facility, and too little time on reading, traveling, sports and movies.

Udayan Ganguly is an Associate Professor at the Department of Electrical Engineering at IIT-Bombay and an active member of the IITBNF community. Apart from his research interests, Prof. Udayan Ganguly is keenly interested in the process of understanding & developing the Ph. D. program and culture. He has written a “Roadmap to a Ph.D.- A Desiderata” that presents the critical processes towards the development of a researcher and a Ph. D. thesis.

IITBNF – A Unique Experience

Those who appreciate the fine precision of a laser-writer, the ultra-low pressure conditions in e-beam evaporators, the ability to detect deposition rates of few angstroms per second in Atomic Layer Deposition (ALD) and Molecular Beam Epitaxy (MBE) systems and the beauty of a lilac hued plasma – they would say “Bingo!” when they get to know IITBNF. For all others, it is just another lab with tremendous expenses. As for me, I have been on both sides!

We usually don’t value the resources at our disposal while we have them. It is only now, when my time here at IIT Bombay is about to end, I realize what an incredible resource this lab has been!

When I started working here at IITBNF, to me, it was just a “chemistry lab with particle control”. But as time passed by, I realized it is so much more than that! One of the many reasons behind this realization was INUP: Indian Nanoelectronics Users Program. This program allows students and faculty from all over India to use the IITBNF facility to execute their fabrication plans & device ideas. To be honest, I was initially really irritated when asked to do a few runs of the dielectric deposition system for INUP members. But then, these users come from various universities and colleges from all over India. So it got me thinking: there must be something unusual about our lab…

The thought hit home when I was performing a metal stack deposition using the e-beam evaporator system. The HMI (Human Machine Interface) was indicating a chamber pressure of 6×10-6 Torr and then it struck me: 1 torr is nearly 1 milli atm pressure. So it implies that the air inside the chamber is nearly a billion times rarer than the air we breathe in!

Some of the devices fabricated here are about a micrometer in size – that is about one tenth of the thickness of a single hair. The fact that electronic devices of such small dimensions can be built here indigenously makes this facility a unique point of interest in India. The word is “neat” when you see how precisely the lithography tools can create a nanometer thick pattern on given semiconductor substrate! An angstrom, as we know, is 10 billionth part of a meter. Imagine the extent of precision that goes into designing machinery that can “detect” a difference of 1 angstrom on a substrate. Incredible, isn’t it? When one closely observes many such details for the first time, one realizes the tremendous potential and value of these equipments and in turn, of the facility! To fathom the importance of this facility in Indian context, here are some statistics: USA and Canada have 88 fabrication labs while Europe has 240. India has just 2 – one being IITBNF!

For me, getting an opportunity to work here has been a rather fortunate and an enlightening experience.

About the author:
“Ashutosh graduated with M.Tech from IITB in July 2015. He worked with Prof. Subhananda Chakrabarti on Quantum Dot Infrared Photodetectors and Intermediate bandgap solar cells – device characterization and fabrication. Post his graduation, he has joined  Applied Micro Circuits Corporation.”