Competitive Landscape

Brainchip have frequently and very publicly declared how superior their technology is to any other market offering. The slide below which was first presented at the Brainchip AGM in May 2021 and subsequently used in numerous investor presentations clearly highlights the Akida advantages over its competitors.

Can this be true? Are Brainchip really this far ahead of their competition? Considering the enormous budgets and huge engineering departments that that the likes of IBM and Intel have at their disposal, this claim to superior functionality and capability deserves some further assessment.

Intel’sLoihi Offering.

The Loihi chip includes a total of some 130,000 neurons, each of which can communicate with thousands of others. Developers can access and manipulate on-chip resources programmatically by means of a learning engine that is embedded in each of the 128 cores. Because the hardware is optimized specifically for SNNs, it supports dramatically accelerated learning in unstructured environments for systems that require autonomous operation and continuous learning, with extremely low power consumption, plus high performance and capacity.

Intel Labs is committed to enabling theresearch community at large with access to test systems based on Loihi. Becausethe technology is still in a research phase (as opposed to production),there are only a limited number of Loihi-based test systems in existence; inorder to expand access, Intel Labs has developed a cloud-based platform forresearch community access to scalable Loihi-based infrastructure.

Intel Labs has established the IntelNeuromorphic Research Community (INRC), a collaborative research effort that brings together teams from academic, government, and industry organizations around the world to overcome the wide-ranging challengesfacing the field of neuromorphic computing.

Its clear from the above extracts taken directly from the Intel website that they currently have no commercial offering in this space and are instead focused on research.

IBM’sTrueNorth offering.

We are not there yet. Indeed, TrueNorth is a direction andnot a destination!

Given this unconventional computing paradigm,compiling C++ to TrueNorth is like using a hammer for a screw. As a result, toharness TrueNorth, we have designed an end-to-end ecosystem complete with a newsimulator, a new programming language, an integrated programming environment,new libraries, new (and old) algorithms as well as applications, and a newteaching curriculum (affectionately called, “SyNAPSE University”). The goal ofthe ecosystem is to dramatically increase programmer productivity.

The above extracts taken from the IBM website indicate that they are struggling with a whole range of productivity and usability challenges.

Brainchip

The fact that the Brainchip Akida offering is relatively simple to use, compatible with the most popular Machine learning languages and tools and requires no new programming languages or skills specific to their product is a big advantage. BrainChip also have a functioning chip that is now in production, fully functioning and ready for commercialisation. Many organisations are already Putting the Brainchip Akida chip through rigorous testing for commercialisation.