What should we learn from...Memories in the Future of Information Processing

You are here

Inside Signal Processing Newsletter Home Page

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

News and Resources for Members of the IEEE Signal Processing Society

What should we learn from...Memories in the Future of Information Processing

In science and engineering, we usually start by defining terms and Axioms-a minimal set-from which a predictive edifice is built. Memory is definable as a frozen representation of an instance of the past. Information, however, has no such clear and concise definition. Shannon’s approach of a sequence of bits and information as the sequence’s separation from randomness can be recast as the number of questions with ‘‘yes’’ and ‘‘no’’ answers to decode the message from the source. Shannon information entirely skirts the issue of bit patterns-the linkages between bits, which certainly has relevance to information. Pattern matching exists as a very successful information processing approach in the natural world and the physical world. The reason for this puzzle, no different from that for entropy, is that information is both objective with symbolic references and subjective with a meaning. It is this latter subjectiveness that makes it opaque for science. This information quandary is also not dissimilar to that of a biologist seeking to define ‘‘life.’’ Biologists use a list of criteria that query the observable effects of ‘‘life,’’ a quite unsatisfactory answer to purists.

What happened in the past matters and it is in this sense that the future of information processing must place memory front and center. Their importance in traditional approach to information processing, whether in on-chip cache or higher level cache and memory, and as storage, is of course quite well recognized.

This is the rationale of the special issue of the Proceedings of the IEEE  in August, Memories in the Future of Information Processing, which aims to explore memories and information processing multidimensionally by not restricting itself to the traditional scaling and deterministic style of the past six plus decades. It is organized to explore, with the future potentiation of information processing, the subject of memory in its multitudinous forms in circuits and systems.

This issue starts with a discussion that connects physics to engineering that information processing and its devices including memory bring together in an integrated ensemble, explores two mainstream emerging memory-oriented directions and then repeats this with a discussion of architectures and their evolution. This sets the stage for a discussion of memory in a deeper sense, by an exploration of the understanding of the brain and a model of its mechanisms. This is followed by a review of the practical implementations of the bioinspired information processing efforts and examples of their successes. T complete this loop of science and its practice by returning to a speculative and advanced theme exploring the questions related to memory in quantum computation.

It is hoped that the reader will find the issue an incisive and appealing peek at the future of information processing in its memory-centric foundations.

It is only by tackling these challenges of the underlying edifice that we will reach domestication of the computer through simplicity from complexity, rather than the state of Marshall McLuhan’s ‘‘the medium is
the message’’ that is currently seen in its daily use in our mobile life.

Sandip Tiwari. Memories in the Future of Information Processing. The Proceedings of the IEEE. 2015, 103(8), pp.1247-1249

Table of Contents:


IEEE SPS Educational Resources

IEEE SPS Resource Center

IEEE SPS YouTube Channel