No software. That’s right. Not even machine code? How does a rigid machine code translate into meaningful applications? So what I would like to know is how are the distributed synaptic memory inputs translated, on-chip, into meaningful outputs? TrueNorth's team have developed their own high-level language, flexible object oriented, to interface TrueNorth on-chip ANN with conventional Von Neumann architecture. How will BrainChip do this? What symbolic method will SNAP use to translate those weighted values stored in BrainChip’s registers into real-world applications for phones or IoT? There has to be some BrainChip software interface for code development. We've heard little about that.
BRN Price at posting:
33.0¢ Sentiment: None Disclosure: Not Held
A personalised tool to help users track selected stocks. Delivering real-time notifications on price updates, announcements, and performance stats on each to help make informed investment decisions.
(20min delay)