Neuron-MOS Temporal Winner Search Hardware for Fully-Parallel Data Processing
نویسندگان
چکیده
A unique architecture of winner search hardware has been developed using a novel neuron-like high functionality device called Neuron MOS transistor (or vMOS in short) [1,2] as a key circuit element. The circuits developed in this work can find the location of the maximum (or minimum) signal among a number of input data on the continuous-time basis, thus enabling real-time winner tracking as well as fully-parallel sorting of multiple input data. We have developed two circuit schemes. One is an ensemble of selfloop-selecting v M OS ring oscillators finding the winner as an oscillating node. The other is an ensemble of vMOS variable threshold inverters receiving a common ramp-voltage for competitive excitation where data sorting is conducted through consecutive winner search actions. Test circuits were fabricated by a double-polysilicon CMOS process and their operation has been experimentally verified.
منابع مشابه
A 1, 000-Neuron System with One Million 7-bit Physical Interconnections
An asynchronous PDM (Pulse-Density-Modulating) digital neural network system has been developed in our laboratory. It consists of one thousand neurons that are physically interconnected via one million 7-bit synapses. It can solve one thousand simultaneous nonlinear first-order differential equations in a fully parallel and continuous fashion. The performance of this system was measured by a wi...
متن کاملParallel Algorithms for Chaotic Exponential Tabu Search Hardware for Quadratic Assignment Problems
The quadratic assignment problem (QAP) is one of the nondeterministic polynomial (NP)-hard combinatorial optimization problems. One of the heuristic algorithms for the QAP is tabu-search. Exponential tabusearch, which is one of improved versions of the tabu search, was proposed using a neural network, and it was further extended to chaotic tabu search with a chaotic neural network. Chaotic dyna...
متن کاملNearest Euclidean Distance Search Associative Memory for High-Speed Pattern Matching
A mixed digital-analog associative memory for Euclidean distance search with fully-parallel processing is reported. Digital processing is used up to subtraction and absolute value calculation in the vector-component comparator part. Analog processing is then applied up to completion of the winner-take-all function. The maximum search time of a test implementation in 0.35 μm CMOS technology havi...
متن کاملTDat: An Efficient Platform for Processing Petabyte-Scale Whole-Brain Volumetric Images
Three-dimensional imaging of whole mammalian brains at single-neuron resolution has generated terabyte (TB)- and even petabyte (PB)-sized datasets. Due to their size, processing these massive image datasets can be hindered by the computer hardware and software typically found in biological laboratories. To fill this gap, we have developed an efficient platform named TDat, which adopts a novel d...
متن کاملUnsupervised Feature Learning With Winner-Takes-All Based STDP
We present a novel strategy for unsupervised feature learning in image applications inspired by the Spike-Timing-Dependent-Plasticity (STDP) biological learning rule. We show equivalence between rank order coding Leaky-Integrate-and-Fire neurons and ReLU artificial neurons when applied to non-temporal data. We apply this to images using rank-order coding, which allows us to perform a full netwo...
متن کامل