Bit-Serial Neural Networks
نویسندگان
چکیده
573 A bit serial VLSI neural network is described from an initial architecture for a synapse array through to silicon layout and board design. The issues surrounding bit serial computation, and analog/digital arithmetic are discussed and the parallel development of a hybrid analog/digital neural network is outlined. Learning and recall capabilities are reported for the bit serial network along with a projected specification for a 64 neuron, bit serial board operating at 20 MHz. This technique is extended to a 256 (2562 synapses) network with an update time of 3ms, using a "paging" technique to time multiplex calculations through the synapse array.
منابع مشابه
Massively-Parallel Bit-Serial Neural Networks for Fast Epilepsy Diagnosis: A Feasibility Study
There are about 1% of the world population suffering from the hidden disability known as epilepsy and major developing countries are not fully equipped to counter this problem. In order to reduce the inconvenience and danger of epilepsy, different methods have been researched by using a artificial neural network (ANN) classification to distinguish epileptic waveforms from normal brain waveforms...
متن کاملOn Serial Multiplication with Neural Networks
In this paper we propose no learning based neural networks for serial multiplication. We show that for “subarray-wise” generation of the partial product matrix and a data transmission rate of -bit per cycle the serial multiplication of two n-bit operands can be computed in n serial cycles with an O(n ) size neural network, and maximum fan-in and weight values both in the order of O( log ). The ...
متن کاملNeural Network Chips for Trigger Purposes in High Energy Physics
Two novel neural chips SAND (Simple Applicable Neural Device) and SIOP (Serial Input Operating Parallel) are described. Both are highly usable for hardware triggers in particle physics. The chips are optimized for a high input data rate at a very low cost basis. The performance of a single SAND chip is 200 MOPS due to four parallel 16 bit multipliers and 40 bit adders working in one clock cycle...
متن کاملLow Weight and Fan-In Neural Networks for Basic Arithmetic Operations
In this paper we investigate low weight and fan-in neural networks for the precise computation of some basic arithmetic operations. First we assume one bit per serial cycle LSB first operand reception and introduce a pipeline network performing serial binary addition in O(n) time constructed with 11 threshold gates, a maximum weight of 2 and a maximum fan-in of 4. Further we prove that serial m...
متن کاملSerial binary multiplication with feed-forward neural networks
In this paper we propose no learning based neural networks for serial binary multiplication. We show that for \subarray-wise" generation of the partial product matrix and a data transmission rate of bits per cycle the serial multiplication of two n-bit operands can be computed in n serial cycles with an O(nn) size neural network, and maximum fan-in and weight values both in the order of O(log)....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1987