![]()
Embedded World in Nuremberg, Germany awaits! | M Anthony Lewis
Embedded World in Nuremberg, Germany awaits! BrainChip's moment to shine! Wednesday of next week, I will be presenting at Embedded World in Nuremberg, Germany, where I will discuss our groundbreaking advancements in Brain-Inspired Computing at BrainChip. Our innovative approach encompasses...www.linkedin.com
View attachment 78801
"You will be able to see the FPGA embodiment "Interesting....................
"At Nuremberg I will be carrying under my arm the what I believe is our most valuable intellectual property to date: an extreme-edge Large Language Model (LLM) that redefines the boundaries of AI deployment. You will be able to see the FPGA embodiment at EW at our booth. While many companies focus on the sheer volume of computation they do at the edge, I believe that the most important computation is the computation that you don't do. What does thinking differently buy us? We will be able to build SoTA systems that operate on a minuscule amounts of power, because the compute is minuscule. The result is silicon so small and cheap it could go anywhere. What if everything you see and touch could be AI powered because power and cost are no longer a limiting factor? This new invention has the potential to to woven into every aspect of your life. It is transformative."
View attachment 78802
TENNs or Akida 2+TeNNs in silicon, albeit in FPGA.
FPGA is an unoptimized version of the circuit constructed from a pre-assembled agglomeration of functional blocks. FPGA is usually a precursor for full ASIC production ... another step closer.
"Achieving state-of-the-art performance across various tasks, including Dynamic Gesture Recognition. "
LLM suggests to me that there could be additional memory to store one or more RAG models (RAG - retrieval-augmented generation) to facilitate swapping models for different purposes?
Last edited: