Jack Vaughan

[May 31, 2022] – I recently watched a documentary on the life of Claude Shannon. “The Bit Player” is a worthwhile piece on the originator of information theory. This caused me to retrieve an Obituary/Appreciation I wrote on his passing in February of 2001. Here I present some of the appreciation part.

Shannon was born in Petoskey, Mich., and grew up in Gaylord, Mich. He worked as a messenger for Western Union while in Gaylord High School, and attended college at MIT, where he was a member of Tau Beta Pi.

His paper, “A Symbolic Analysis of Relay and Switching Circuits,” which led to a long association with Bell Laboratories, laid out Shannon’s theories on the relationship of symbolic logic and relay circuits.

While at Bell Labs, Shannon wrote the landmark “The Mathematical Theory of Communication.” The information content of a message, he theorized, consists simply of the number of 1’s and 0’s it takes to transmit it. In a real sense, Shannon conceived of the “bit” that is now so widely used to represent data.

Shannon’s work led to many inventions used by both technology developers and end users. His theories can truly be described as pervasive today.

When I was young, Shannon’s work was a tough nut to crack, but it certainly was intriguing. As a high school boy, I was interested in the future — maybe more so than now, when I live and breathe and work in what that future became. Grappling with Shannon’s basic information theories was part of my education about the future.

Growing up in a Wisconsin city across the lake from Shannon’s birthplace, I tried to plow through the town library as best I could. I wanted to learn about computers, automation, and the combination of the two that was known in those days (the 1960s) as cybermation.* I discovered for myself — by chance, really — that the fundamental elements of those ideas were Shannon’s inventions.

Much of his greatest work revolved around defining information in relation to “noise,” the latter phenomenon being quite familiar to anyone who often tried desperately to home in on radio signals before digital communication filters came into being. I came to appreciate that aspect of Shannon’s work later on when, as a journalist, I had the opportunity to learn and write about digital signal processing.

Day and night, data, messages, music, and more swirls around us — all made possible to some extent by the idea of communicating electronically in 1’s and 0’s. It is something to think that a Western Union messenger could have conceived of this new world.

~~~~~~~~~~~~~~~~~

Postscript: Of course, Shannon did not envisage or invent PacMan or Puff Daddy MP3s – tho the documentary shows him to be a great fan of shellac jazz. He imagined the river for others to sail. This conjures the words of Herbert Kroemer, inventor of heterostructures that changed evolution of ICs and commercial optics. “A pendulum … goes back and forth from science to applications. Science creates applications … [they] stimulate new science-it’s not one way or the other,” Kroemer said in a Nobelist interview.

Now read the rest of the story –  Digital pioneer Claude Shannon dead at 84 – Computerworld – Feb 28, 2001

~~~~~~~~~~~~~~~~~

* I think we meant ‘cybernetics’.

Listen to article  |  5 min

[February 19, 2022] – Earlier this month IARPA announced $4.8 million in funding for a project that is led by Boston-based electro-photonic computing startup Lightmatter and which is joined by BU and Harvard researchers. IARPA has conceptual affinity with DARPA, the Defense Dept.’s long-time running technology seeding lab, but in IARPA’s case the funding comes out of the Office of the Director of National Intelligence.

Lightmatter’s photonic computing efforts to date have centered on the idea of a supercomputer based on photonic silicon hybrid chips that specialize in performing large matrix computations. Proponents see the photonic domain as a logical next step beyond electronics, as the window on Moore’s Law closes. While barriers are significant, the photonic approach arguably requires shorter leaps forward than  quantum computing techniques that have been extensively covered in the press. It seems photonic computing as represented in efforts by  Lightmatter and others could be reasonably added to the basket of strange new brews being applied in the search for better AI processing today.

While optical data communications are well established – think “The Internet” — it’s early going for computing based on light waves. Lightmatter is one of few that has created photonic arrays that are capable of computation and which are matched with layers of digital and analog electronics that take care of much of the activity auxiliary to such computation.

A prototype board based on its chip was shown last year, as well as a box with six such chips and boards. So, any supercomputer is in the future.

Note that IARPA’s interest here is at the other end of the computing spectrum — farther from the data center, and closer to the edge. Among the obstacles Edge AI faces is power consumption, and today’s approaches to AI tend to use a lot of it.

Analog processing that calculates in memory has been put forward as a way to avoid costly (in power terms) movement of data from processor to memory in this way. The Lightmatter crew and others take a different tact. They see the optical domain as another way to save trips to memory for multiply-accumulate work that marks today’s neural nets for AI. Lightmatter is not alone in the quest.

Lightmatter is led by Nicholas Harris, a former MIT researcher whose interest in how computers work pans right down to the atomic sale, and which has led him to explore ways of coupling deep learning and Electro-Photonic Computing. His experience is by no means solely in the academic lab, as he served for a time as an R&D lead at Micron Technology in the high country of Idaho from where he originated. Lightmatter has raised more than $113 million from investors including Google Ventures and Spark Capital.

Edge AI-based silicon photonics is a bridge afar. Early going means basic chip architecture and processes need to be worked out before reliability, scalability and cost can be determined. There are still multiple approaches being taken to building in quite basic functionality as on-chips component. For example, how do assure that you are effectively shuttling light on chip? For its part, Lightmatter uses a MEMS-like structure which they call NOEMS, for “nano-opto-electro-mechanical”, based on phase shifters that operate at CMOS-compatible voltages. In effect this method guides a wave with the force of electrostatic charge, I think.

Cost is not an issue for IARPA, which is likely looking to improve the reach and ability of surveillance drones. But there are a lot of ramifications to this work If the present project bears fruit, it could further photonic computation in general terms, not just for AI apps. Moreover, what furthers photonic computation could also help spur quantum computing advancement.

A 2021 funding round saw Lightmatter gain backing from no less than he round was led by Viking Global Investors with participation from GV (formerly Google Ventures), Hewlett Packard Enterprise (HPE), Lockheed Martin, Matrix Partners, SIP Global Partners, Spark Capital, and others. – Jack Vaughan

IARPA project press release – Businesswire
Company site – Lightmatter
Citations/Nick Harris – Google Scholar
Useful silicon photonic back rounder – Ghent U.
Sally Ward-Foxton Lightmatter coverage from HotChips 2021 – EETimes