No abstract

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...

Here we report organic light-emitting diodes incorporating linear and cyclic porphyrin hexamers which have red-shifted emission (λ(PL) = 873 and 920 nm, respectively) compared to single porphyrin rings as a consequence of their extended π-conjugation. We studied the photoluminescence and electroluminescence of blends with poly(9,9'-dioctylfluorene-alt-benzothiadiazole), demonstrating a high photoluminescence quantum efficiency of 7.7% for the linear hexamer when using additives to prevent aggregation and achieving high color purity near-infrared electroluminescence.

Winner-Take-All (WTA) networks are recurrently connected populations of excitatory and inhibitory neurons that represent promising candidate microcircuits for implementing cortical computation. WTAs can perform powerful computations, ranging from signal-restoration to state-dependent processing. However, such networks require fine-tuned connectivity parameters to keep the network dynamics within stable operating regimes. In this article, we show how such stability can emerge autonomously through an interaction of biologically plausible plasticity mechanisms that operate simultaneously on all excitatory and inhibitory synapses of the network. A weight-dependent plasticity rule is derived from the triplet spike-timing dependent plasticity model, and its stabilization properties in the mean-field case are analyzed using contraction theory. Our main result provides simple constraints on the plasticity rule parameters, rather than on the weights themselves, which guarantee stable WTA behavior. The plastic network we present is able to adapt to changing input conditions, and to dynamically adjust its gain, therefore exhibiting self-stabilization mechanisms that are crucial for maintaining stable operation in large networks of interconnected subunits. We show how distributed neural assemblies can adjust their parameters for stable WTA function autonomously while respecting anatomical constraints on neural wiring.

Event cameras, such as dynamic vision sensors (DVS), and dynamic and activepixel vision sensors (DAVIS) can supplement other autonomous driving sensors by providing a concurrent stream of standard active pixel sensor (APS) images and DVS temporal contrast events. The APS stream is a sequence of standard grayscale global-shutter image sensor frames. The DVS events represent brightness changes occurring at a particular moment, with a jitter of about a millisecond under most lighting conditions. They have a dynamic range of >120 dB and effective frame rates >1 kHz at data rates comparable to 30 fps (frames/second) image sensors. To overcome some of the limitations of current image acquisition technology, we investigate in this work the use of the combined DVS and APS streams in endto-end driving applications. The dataset DDD17 accompanying this paper is the first open dataset of annotated DAVIS driving recordings. DDD17 has over 12 h of a 346x260 pixel DAVIS sensor recording highway and city driving in daytime, evening, night, dry and wet weather conditions, along with vehicle speed, GPS position, driver steering, throttle, and brake captured from the car's on-board diagnostics interface. As an example application, we performed a preliminary end-toend learning study of using a convolutional neural network that is trained to predict the instantaneous steering angle from DVS and APS visual data.

Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For example, Transformers segment by position, and object-centric architectures decompose images into entities. In all these architectures, interactions between different elements are modeled via pairwise interactions: Transformers make use of selfattention to incorporate information from other positions; object-centric architectures make use of graph neural networks to model interactions among entities. However, pairwise interactions may not achieve global coordination or a coherent, integrated representation that can be used for downstream tasks. In cognitive science, a global workspace architecture has been proposed in which functionally specialized components share information through a common, bandwidthlimited communication channel. We explore the use of such a communication channel in the context of deep learning for modeling the structure of complex environments. The proposed method includes a shared workspace through which communication among different specialist modules takes place but due to limits on the communication bandwidth, specialist modules must compete for access. We show that capacity limitations have a rational basis in that (1) they encourage specialization and compositionality and (2) they facilitate the synchronization of otherwise independent specialists.

Neuromorphic event cameras are useful for dynamic vision problems under difficult lighting conditions. To enable studies of using event cameras in automobile driving applications, this paper reports a new end-to-end driving dataset called DDD20. The dataset was captured with a DAVIS camera that concurrently streams both dynamic vision sensor (DVS) brightness change events and active pixel sensor (APS) intensity frames. DDD20 is the longest event camera end-to-end driving dataset to date with 51h of DAVIS event+frame camera and vehicle human control data collected from 4000km of highway and urban driving under a variety of lighting conditions. Using DDD20, we report the first study of fusing brightness change events and intensity frame data using a deep learning approach to predict the instantaneous human steering wheel angle. Over all day and night conditions, the explained variance for human steering prediction from a Resnet-32 is significantly better from the fused DVS+APS frames (0.88) than using either DVS (0.67) or APS (0.77) data alone.

The biological plausibility of the backpropagation algorithm has long been doubted by neuroscientists. Two major reasons are that neurons would need to send two different types of signal in the forward and backward phases, and that pairs of neurons would need to communicate through symmetric bidirectional connections. We present a simple two-phase learning procedure for fixed point recurrent networks that addresses both these issues. In our model, neurons perform leaky integration and synaptic weights are updated through a local mechanism. Our learning method generalizes Equilibrium Propagation to vector field dynamics, relaxing the requirement of an energy function. As a consequence of this generalization, the algorithm does not compute the true gradient of the objective function, but rather approximates it at a precision which is proven to be directly related to the degree of symmetry of the feedforward and feedback weights. We show experimentally that our algorithm optimizes the objective function.