The way machine learning is implemented in hardware (and digital described in a HDL) is going to evolve. New architectures will be thought of, new ways of processing the data will be invented. Machine learning will require better and better custom hardware. At some point, machine learning would be so fast and be able to handle complex tasks. So, in the end, machines will design the machines themselves. We are now in the slow part of an exponential curve. Nobody can accurately predict when this happens, but it is unavoidable that machines become smart enough to develop machines themselves, which would be the fast exponential part of the curve.
Hardware and software advisor for tech startups. ASIC, FPGA, RPi, Arduino, AI, robots, drones, blockchain, Machine learning, vision processing, IoT and 3D printers are my fields of expertise.