Adaptive Neuromorphic Architecture (ANA)

Wang, Frank Z.; Chua, Leon O.; Yang, Xin‐She; Helian, Na; Tetzlaff, Ronald; Schmidt, Torsten; Li, Caroline; Carrasco, José Manuel García; Chen, Wanlong; Chu, Dominique

doi:10.1016/j.neunet.2013.02.009

Cited by 40 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The circuit’s resonance frequency, determined by the staircased L ( q ) ( Figure 3 ) , increases itself with the increased number of oncoming stimulus pulses. This simulation in Figure 8 a agrees with our experiment in Figure 8 b on a hardware emulator built with a dsPIC30F2011 microcontroller, an MCP4261 digital potentiometer and a differential 12-bit ADC converter [ 15 ].…”

Section: Simulations and Experiments Of A Coil Core Meminductor For N...supporting

confidence: 85%

“…Taking amoebae as an example, they display memorizing, timing and anticipating mechanisms, which may represent the origins of primitive learning. A circuit element with memory can be used to mimic these behaviors in terms of being plastic according to the dynamic history [ 13 , 14 , 15 ].…”

Section: Simulations and Experiments Of A Coil Core Meminductor For N...mentioning

confidence: 99%

See 1 more Smart Citation

Beyond Memristors: Neuromorphic Computing Using Meminductors

Wang

2023

Micromachines

Self Cite

View full text Add to dashboard Cite

Resistors with memory (memristors), inductors with memory (meminductors) and capacitors with memory (memcapacitors) play different roles in novel computing architectures. We found that a coil with a magnetic core is an inductor with memory (meminductor) in terms of its inductance L(q) being a function of charge q. The history of the current passing through the coil is remembered by the magnetization inside the magnetic core. Such a meminductor can play a unique role (that cannot be played by a memristor) in neuromorphic computing, deep learning and brain-inspired computers since the time constant (t0=LC) of a neuromorphic RLC circuit is jointly determined by the inductance L and capacitance C, rather than the resistance R. As an experimental verification, this newly invented meminductor was used to reproduce the observed biological behavior of amoebae (the memorizing, timing and anticipating mechanisms). In conclusion, a beyond-memristor computing paradigm is theoretically sensible and experimentally practical.

show abstract

Section: Simulations and Experiments Of A Coil Core Meminductor For N...supporting

confidence: 85%

Section: Simulations and Experiments Of A Coil Core Meminductor For N...mentioning

confidence: 99%

Beyond Memristors: Neuromorphic Computing Using Meminductors

Wang

2023

Micromachines

Self Cite

View full text Add to dashboard Cite

show abstract

“…For convenience, we use conductance, which is proportional to synaptic weight as used in computer science or synaptic strength as used in neuroscience, when we refer to memristor device. two-terminal devices using various material systems [13]- [19], [38]- [42]. Fig.…”

Section: A Memristor As Synapsementioning

confidence: 99%

Homogeneous Spiking Neuromorphic System for Real-World Pattern Recognition

Saxena

Zhu

2015

IEEE J. Emerg. Sel. Topics Circuits Syst.

View full text Add to dashboard Cite

Abstract-A neuromorphic chip that combines CMOS analog spiking neurons and memristive synapses offers a promising solution to brain-inspired computing, as it can provide massive neural network parallelism and density. Previous hybrid analog CMOS-memristor approaches required extensive CMOS circuitry for training, and thus eliminated most of the density advantages gained by the adoption of memristor synapses. Further, they used different waveforms for pre and post-synaptic spikes that added undesirable circuit overhead. Here we describe a hardware architecture that can feature a large number of memristor synapses to learn real-world patterns. We present a versatile CMOS neuron that combines integrate-and-fire behavior, drives passive memristors and implements competitive learning in a compact circuit module, and enables in-situ plasticity in the memristor synapses. We demonstrate handwritten-digits recognition using the proposed architecture using transistor-level circuit simulations. As the described neuromorphic architecture is homogeneous, it realizes a fundamental building block for large-scale energy-efficient brain-inspired silicon chips that could lead to next-generation cognitive computing.

show abstract

“…However, this may not be practical in real life situations. Recent progresses in designing adaptive neuromorphic architectures suggest (Wang et al, 2013) that in the next future will be possible to overcome this problem by implementing adaptive temporal binning schemes in hardware. By using such adaptive architectures, it may be possible to design acquisition hardware that self-adjusts its inherent parameters (for instance, the working frequency of the sample-and-hold circuit) naturally following the neural activity variability.…”

Section: Discussionmentioning

confidence: 99%

State-Dependent Decoding Algorithms Improve the Performance of a Bidirectional BMI in Anesthetized Rats

et al. 2017

View full text Add to dashboard Cite

Brain-machine interfaces (BMIs) promise to improve the quality of life of patients suffering from sensory and motor disabilities by creating a direct communication channel between the brain and the external world. Yet, their performance is currently limited by the relatively small amount of information that can be decoded from neural activity recorded form the brain. We have recently proposed that such decoding performance may be improved when using state-dependent decoding algorithms that predict and discount the large component of the trial-to-trial variability of neural activity which is due to the dependence of neural responses on the network's current internal state. Here we tested this idea by using a bidirectional BMI to investigate the gain in performance arising from using a state-dependent decoding algorithm. This BMI, implemented in anesthetized rats, controlled the movement of a dynamical system using neural activity decoded from motor cortex and fed back to the brain the dynamical system's position by electrically microstimulating somatosensory cortex. We found that using state-dependent algorithms that tracked the dynamics of ongoing activity led to an increase in the amount of information extracted form neural activity by 22%, with a consequently increase in all of the indices measuring the BMI's performance in controlling the dynamical system. This suggests that state-dependent decoding algorithms may be used to enhance BMIs at moderate computational cost.

show abstract

Adaptive Neuromorphic Architecture (ANA)

Cited by 40 publications

References 12 publications

Beyond Memristors: Neuromorphic Computing Using Meminductors

Beyond Memristors: Neuromorphic Computing Using Meminductors

Homogeneous Spiking Neuromorphic System for Real-World Pattern Recognition

State-Dependent Decoding Algorithms Improve the Performance of a Bidirectional BMI in Anesthetized Rats

Contact Info

Product

Resources

About