Yeo et al., 2019 - Google Patents
A CMOS-based Resistive Crossbar Array with Pulsed Neural Network for Deep Learning AcceleratorYeo et al., 2019
- Document ID
- 471897838624844442
- Author
- Yeo I
- Gi S
- Kim J
- Lee B
- Publication year
- Publication venue
- 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)
External Links
Snippet
A CMOS-based resistive computing element (RCE), which can be integrated in a crossbar array, is presented. The RCE successfully solves the hardware constraints of the existing memristive devices such as dynamic ranges of conductance, IV nonlinearity, and on/off ratio …
- 230000001537 neural 0 title abstract description 22
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computer systems based on biological models
- G06N3/02—Computer systems based on biological models using neural network models
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
- G06N3/0635—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means using analogue means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computer systems based on biological models
- G06N3/02—Computer systems based on biological models using neural network models
- G06N3/04—Architectures, e.g. interconnection topology
-
- H—ELECTRICITY
- H03—BASIC ELECTRONIC CIRCUITRY
- H03K—PULSE TECHNIQUE
- H03K3/00—Circuits for generating electric pulses; Monostable, bistable or multistable circuits
- H03K3/02—Generators characterised by the type of circuit or by the means used for producing pulses
-
- H—ELECTRICITY
- H03—BASIC ELECTRONIC CIRCUITRY
- H03K—PULSE TECHNIQUE
- H03K3/00—Circuits for generating electric pulses; Monostable, bistable or multistable circuits
- H03K3/01—Details
- H03K3/012—Modifications of generator to improve response time or to decrease power consumption
-
- H—ELECTRICITY
- H03—BASIC ELECTRONIC CIRCUITRY
- H03K—PULSE TECHNIQUE
- H03K19/00—Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits
- H03K19/02—Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components
- H03K19/08—Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits using specified components using semiconductor devices
- H03K19/0813—Threshold logic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING; COUNTING
- G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N99/00—Subject matter not provided for in other groups of this subclass
- G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sun et al. | Exploiting hybrid precision for training and inference: A 2T-1FeFET based analog synaptic weight cell | |
US9779355B1 (en) | Back propagation gates and storage capacitor for neural networks | |
Kim et al. | Analog CMOS-based resistive processing unit for deep neural network training | |
Levy et al. | Logic operations in memory using a memristive Akers array | |
Adam et al. | Memristive LSTM network hardware architecture for time-series predictive modeling problems | |
Kang et al. | An energy-efficient memory-based high-throughput VLSI architecture for convolutional networks | |
US5696883A (en) | Neural network expressing apparatus including refresh of stored synapse load value information | |
Manem et al. | Stochastic gradient descent inspired training technique for a CMOS/nano memristive trainable threshold gate array | |
Hassan et al. | Voltage-driven building block for hardware belief networks | |
US20190147328A1 (en) | Competitive machine learning accuracy on neuromorphic arrays with non-ideal non-volatile memory devices | |
Liu et al. | Reconfigurable neuromorphic computing system with memristor-based synapse design | |
Kaiser et al. | Probabilistic circuits for autonomous learning: A simulation study | |
Molin et al. | Low-power, low-mismatch, highly-dense array of VLSI Mihalas-Niebur neurons | |
Lim et al. | Highly reliable inference system of neural networks using gated Schottky diodes | |
Liu et al. | The circuit realization of a neuromorphic computing system with memristor-based synapse design | |
Yeo et al. | Stochastic implementation of the activation function for artificial neural networks | |
Yeo et al. | A CMOS-based Resistive Crossbar Array with Pulsed Neural Network for Deep Learning Accelerator | |
Oshio et al. | A memcapacitive spiking neural network with circuit nonlinearity-aware training | |
Asghar et al. | Current multiplier based synapse and neuron circuits for compact SNN chip | |
Gi et al. | A ReRAM-based convolutional neural network accelerator using the analog layer normalization technique | |
US10949738B1 (en) | Tunable memristor noise control | |
Chen et al. | A programmable calculation unit employing memcapacitor-based neuromorphic circuit | |
James et al. | Inference dropouts in binary weighted analog memristive crossbar | |
Basford et al. | The impact of analog computational error on an analog boolean satisfiability solver | |
Taylor et al. | CMOS Implementation of Spiking Equilibrium Propagation for Real-Time Learning |