CrabmansFriend
Regular
My 2 cents, I value 4 things positive (although for my taste one/some deal announcement(s) need to follow this year):
1. André van Schaik has been added to the Scientific Advisory Board.
There has been an interview/podcast with him at eetimes/brains & machines (https://www.eetimes.com/podcasts/andre-van-schaik-discusses-new-neuromorphic-simulator/) where he states:
2. So, although I don't know how our (current "hardware") IP might be of use inside of a FPGA, I see it as a positive we are getting closer not only to sensors but also these type of semiconductors. In combination with André van Schaik's field of research, to me that sounds like Brainchip is trying to evaluate the usage of Akida also at the opposite end of the spectrum (closer to servers/cloud/HPC). Additionally, some of the most important vendors of FPGAs are Intel, AMD. Can't hurt getting a bit more active in this area, especially as industry trends besides GPUs for HPC, ASICs for specific tasks (at the edge) seems to be trying a 3rd direction by keeping the hardware as flexible as possible for all the use cases in between while the field of ML/AI is progressing so fast and changing constantly.
3. "Development of an Akida 2.0 derivative to support LLM (Large Language Models) on edge devices"
Good that Dr. Eshraghian ("his lab developed [...] SpikeGPT") has also been added to our Scientific Advisory Board.
4. Funding via LDA capital probably not needed anymore, at least for this year. Could help the stock price recover a bit.
Brainchip, please let me know when you finally start considering chiplets
.
1. André van Schaik has been added to the Scientific Advisory Board.
There has been an interview/podcast with him at eetimes/brains & machines (https://www.eetimes.com/podcasts/andre-van-schaik-discusses-new-neuromorphic-simulator/) where he states:
Now a problem for spiking neural networks, which is what we’re interested in at the moment because brains are spiking neural networks, is that they are terrible to simulate on a computer—it’s very slow to do large networks. And so, I want to create a technology that enables you to simulate these large-scale spiking neural networks in a reasonable amount of time.
And I want to do it in such a way that we don’t build our own chips for this, but that we use commercial hardware instead. Because similar to the GPU, was not developed for neural networks. It was a technology that was commercially done for graphical processing on computers. FPGAs’ reconfigurable hardware is another commercial technology that’s being used for various applications, and one application that we think it’s good for is simulating spiking neural networks.
2. So, although I don't know how our (current "hardware") IP might be of use inside of a FPGA, I see it as a positive we are getting closer not only to sensors but also these type of semiconductors. In combination with André van Schaik's field of research, to me that sounds like Brainchip is trying to evaluate the usage of Akida also at the opposite end of the spectrum (closer to servers/cloud/HPC). Additionally, some of the most important vendors of FPGAs are Intel, AMD. Can't hurt getting a bit more active in this area, especially as industry trends besides GPUs for HPC, ASICs for specific tasks (at the edge) seems to be trying a 3rd direction by keeping the hardware as flexible as possible for all the use cases in between while the field of ML/AI is progressing so fast and changing constantly.
3. "Development of an Akida 2.0 derivative to support LLM (Large Language Models) on edge devices"
Good that Dr. Eshraghian ("his lab developed [...] SpikeGPT") has also been added to our Scientific Advisory Board.
4. Funding via LDA capital probably not needed anymore, at least for this year. Could help the stock price recover a bit.
Brainchip, please let me know when you finally start considering chiplets