Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit

Hahnloser, Richard H. R.; Sarpeshkar, Rahul; Mahowald, Misha; Douglas, Rodney J.; Seung, H. Sebastian

doi:10.1038/35016072

Cited by 1,044 publications

(538 citation statements)

References 24 publications

Supporting

Mentioning

529

Contrasting

Unclassified

Order By: Relevance

“…Among other functions, these networks can also be configured as SSMs (16,18). However, these SSMs are unlike their classical digital counterparts, in that they combine digital selection with analog signal processing properties (45), an intriguing duality that we have exploited here. Also the sWTA networks used to implement SSMs differ from digital systems, in that they restore their input signals toward patterns stored in their connections, rather than toward logic levels (Fig.…”

Section: Discussionmentioning

confidence: 99%

“…First, it provides computational primitives on which behaviors are easily cast and learned. Second, these primitives provide basic signal processing properties necessary for steering and stabilizing processing such as signal gain, signal restoration (17), and multistability (45). Finally, the layer of primitives hides the details and variability of the neuronal hardware implementation from the behavioral level.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Synthesizing cognition in neuromorphic electronic systems

Neftci

Binas

Rutishauser

et al. 2013

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

125

122

View full text Add to dashboard Cite

The quest to implement intelligent processing in electronic neuromorphic systems lacks methods for achieving reliable behavioral dynamics on substrates of inherently imprecise and noisy neurons. Here we report a solution to this problem that involves first mapping an unreliable hardware layer of spiking silicon neurons into an abstract computational layer composed of generic reliable subnetworks of model neurons and then composing the target behavioral dynamics as a "soft state machine" running on these reliable subnets. In the first step, the neural networks of the abstract layer are realized on the hardware substrate by mapping the neuron circuit bias voltages to the model parameters. This mapping is obtained by an automatic method in which the electronic circuit biases are calibrated against the model parameters by a series of population activity measurements. The abstract computational layer is formed by configuring neural networks as generic soft winner-take-all subnetworks that provide reliable processing by virtue of their active gain, signal restoration, and multistability. The necessary states and transitions of the desired high-level behavior are then easily embedded in the computational layer by introducing only sparse connections between some neurons of the various subnets. We demonstrate this synthesis method for a neuromorphic sensory agent that performs real-time context-dependent classification of motion patterns observed by a silicon retina.decision making | sensorimotor | working memory | analog very large-scale integration | artificial neural systems U nlike digital simulations, in which the dynamics of neuronal models are encoded and calculated on general purpose digital hardware, "neuromorphic" emulations express the dynamics of the neural systems directly on an analogous physical substrate (1). Digital simulations have the advantage that they can be exactly and reliably programmed using numerical operations of very high precision. However, they suffer the disadvantage that they are cast on abstract binary electronic circuits whose operation is entirely divorced from the physical processes being simulated. Consequently, such simulations do not readily advance our understanding of how biological neural systems are able to attain their extraordinary physical performance, using only large numbers of apparently unreliable, slow, and imprecise neural components, a problem first recognized by von Neumann more than a half century ago (2). Furthermore, the reliability of digital systems comes at high cost of the circuit complexity necessary for the orchestration of communication and processing, an overhead that declares itself also in the costs of system construction and power dissipation (3).The alternative, neuromorphic, approach to information processing strives to capture in complementary metal-oxide semiconductor (CMOS) very large-scale integration (VLSI) electronic technology the more distributed, asynchronous, and limited precision nature of biological intelligent systems (1, 4).†, ‡ Research...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Synthesizing cognition in neuromorphic electronic systems

Neftci

Binas

Rutishauser

et al. 2013

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

125

122

View full text Add to dashboard Cite

show abstract

“…The non-linearity of a network is contributed by activation layers, and it ensures that the network is able to handle non-linear problems. Activation layers are usually attached to convolution layers with the element-wise operation, where the most popular activation functions are ReLU [27] and its variants [26,28].…”

Section: Fully Convolutional Network Frameworkmentioning

confidence: 99%

Automatic Raft Labeling for Remote Sensing Images via Dual-Scale Homogeneous Convolutional Neural Network

Shi

Zou

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Raft-culture is a way of utilizing water for farming aquatic product. Automatic raft-culture monitoring by remote sensing technique is an important way to control the crop's growth and implement effective management. This paper presents an automatic pixel-wise raft labeling method based on fully convolutional network (FCN). As rafts are always tiny and neatly arranged in images, traditional FCN method fails to extract the clear boundary and other detailed information. Therefore, a homogeneous convolutional neural network (HCN) is designed, which only consists of convolutions and activations to retain all details. We further design a dual-scale structure (DS-HCN) to integrate higher-level contextual information for accomplishing sea-land segmentation and raft labeling at the same time in a uniform framework. A dataset with Gaofen-1 satellite images was collected to verify the effectiveness of our method. DS-HCN shows a satisfactory performance with a better interpretability and a more accurate labeling result.

show abstract

“…For an input image of 256 × 256 pixels the grouping of those 65536 feature vectors would take several hours. Note, that the network type of the CLM could also be implemented in silicon in a biologically plausible way (Hahnloser, Sarpeshkar, Mahowald, Douglas, & Seung, 2000). For the sequential processing of the dynamics on a single processor, we subsampled the 4 feature images obtained by the projection onto the first 4 principal components.…”

Section: Feature Subsamplingmentioning

confidence: 99%

A computational feature binding model of human texture perception

Ontrup

Wersing²,

Ritter

2004

Cognitive Processing

View full text Add to dashboard Cite

We present a computational model for human texture perception which assigns functional principles to the Gestalt laws of similarity and proximity. Motivated by early vision mechanisms, in a first step local texture features are extracted by utilizing multi-scale filtering and non-linear spatial pooling. In the second stage, features are grouped according to the spatial feature binding model of the Competitive Layer Model (CLM) (Wersing, Steil, & Ritter, 2001). The CLM uses cooperative and competitive interactions in a recurrent network, where binding is expressed by the layer-wise coactivation of feature-representing neurons. The Gestalt law of similarity is expressed by a non-euclidean distance measure in the abstract feature space with proximity being taken into account by a spatial component. To choose the stimulus dimensions which allow the most salient similarity-based texture segmentation, the feature similarity metrics is reduced to the directions of maximum variance. We show that our combined texture feature extraction and binding model performs segmentation in strong conformity with human perception. The examples range from classical microtextures and Brodatz textures to other classical Gestalt stimuli, which offer a new perspective on the role of texture for more abstract similarity grouping.

show abstract

Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit

Cited by 1,044 publications

References 24 publications

Synthesizing cognition in neuromorphic electronic systems

Synthesizing cognition in neuromorphic electronic systems

Automatic Raft Labeling for Remote Sensing Images via Dual-Scale Homogeneous Convolutional Neural Network

A computational feature binding model of human texture perception

Contact Info

Product

Resources

About