Feature: Processors


Figure 1: The human perception of voice according to Karl Friston’s Free Energy Theory


over the past 20 years, mainly focused on parallel processing developments, resulting in a certain level of parallelism of Graphics Processing Unit (GPU) and Tensor Processing Unit (TPU) – AI accelerator ASIC – solutions. However, the energy consumption problem was not resolved, especially since there is intensive exchange with memory within these units. Increasing the number of processing units also adds to the power budget. By comparison, billions of years of


evolutionary development has led to the human brain to consume only 20W, despite its 80 billion neurons, leading to the development of analogue neuromorphic designs for effi cient neural network implementation. Neuromorphic analogue computing mimics the brain’s function and effi ciency by building artifi cial neural systems that implement “neurons” and “synapses”, to transfer electrical signals in analogue circuit design. Analogue neuromorphic ICs are intrinsically parallel and better adapted for neural network operations. An analogue neuromorphic model of


a single neuron with a fi xed resistor as weights representation is better than a digital model, because N multibit MAC operations in analogue essentially require N+1 resistors, whilst in digital they normally require N*(10~40) transistors per bit, or N*(80~320) transistors for 8-bit precision. T erefore, the analogue


neuromorphic model is fundamentally superior in terms of single-neuron performance. Any current disadvantages of analogue circuits are not fundamental and are only related to some engineering challenges. T e most important advantage of digital


solutions is the possibility of reusing a single computational block (i.e., an ALU or a hardware multiplier) many times whilst feeding it new weights and data. However, this approach creates a memory- related power bottleneck, since data transfer becomes more energy-consuming than the computations themselves. Current eff orts are being undertaken to


make analogue neural network processors mostly use the in-memory computing approach.


In-memory approach In-memory computing addresses the memory problem, but because it puts all the weights on a chip in crossbars, it suff ers from a large chip area. Another problem of in-memory


computing is poor area utilisation. On one hand, the memory array can’t be too small (memory cell overhead dominating the area is not effi cient); on the other, the memory crossbar is an all-to-all connection, but the possible number of inputs for each neuron is limited by noise. So, if the array is too big, most memory cells are useless, which creates a signifi cant


area overhead. In practice, memory utilisation is not more than 40-50%, even when the network is optimised for the hardware, and such hardware optimisation signifi cantly constrains the network architecture. Typical arrays are limited to 256-512 cells in width and height, whereas reasonably small networks may easily have 2,000-4,000 neurons in a single layer. Another limitation of in-memory


computing is limited precision, a measure of quality. T e SRAM is one bit per cell, whereas existing Flash memory is up to 4-5 bits per cell. Other types of in-memory options


(MRAM, PCM, ReRAM, FeRAM) rate low in TRL (technology readiness level) and don’t promise multibit production-level solutions in the next few years.


AI Karl Friston, a leading scientist in the area of neurophysiology and AI, proposed the Free Energy T eory, which suggests that brain connections minimise entropy of making representations that predict sensory signals. T is model of the environment is built on the basis of sensory information and its interpretation; more information input results in a more complex model of the environment. T e Friston concept does not limit itself to brain operation and is valid for any AI system. According to neurobiological research, the retina, visual nerve and some areas of


www.electronicsworld.co.uk July/August 2022 19


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52