Symmetry perception with spiking neural networks

Artificial optoelectronic spiking neuron based on a resonant tunnelling diode coupled to a vertical cavity surface emitting laser

Excitable optoelectronic devices represent one of the key building blocks for implementation of artificial spiking neurons in neuromorphic (brain-inspired) photonic systems. This work introduces and experimentally investigates an opto-electro-optical (O/E/O) artificial neuron built with a resonant tunnelling diode (RTD) coupled to a photodetector as a receiver and a vertical cavity surface emitting laser as a transmitter. We demonstrate a well-defined excitability threshold, above which the neuron produces optical spiking responses with characteristic neural-like refractory period. We utilise its fan-in capability to perform in-device coincidence detection (logical AND) and exclusive logical OR (XOR) tasks. These results provide first experimental validation of deterministic triggering and tasks in an RTD-based spiking optoelectronic neuron with both input and output optical (I/O) terminals. Furthermore, we also investigate in simulation the prospects of the proposed system for nanophotonic implementation in a monolithic design combining a nanoscale RTD element and a nanolaser; therefore demonstrating the potential of integrated RTD-based excitable nodes for low footprint, high-speed optoelectronic spiking neurons in future neuromorphic photonic hardware.

Recurrent connections facilitate symmetry perception in deep networks

Symmetry is omnipresent in nature and perceived by the visual system of many species, as it facilitates detecting ecologically important classes of objects in our environment. Yet, the neural underpinnings of symmetry perception remain elusive, as they require abstraction of long-range spatial dependencies between image regions and are acquired with limited experience. In this paper, we evaluate Deep Neural Network (DNN) architectures on the task of learning symmetry perception from examples. We demonstrate that feed-forward DNNs that excel at modelling human performance on object recognition tasks, are unable to acquire a general notion of symmetry. This is the case even when the feed-forward DNNs are architected to capture long-range spatial dependencies, such as through 'dilated' convolutions and the 'transformers' design. By contrast, we find that recurrent architectures are capable of learning a general notion of symmetry by breaking down the symmetry's long-range spatial dependencies into a progression of local-range operations. These results suggest that recurrent connections likely play an important role in symmetry perception in artificial systems, and possibly, biological ones too.

Towards Generalizing the Information Theory for Neural Communication

Neuroscience extensively uses the information theory to describe neural communication, among others, to calculate the amount of information transferred in neural communication and to attempt the cracking of its coding. There are fierce debates on how information is represented in the brain and during transmission inside the brain. The neural information theory attempts to use the assumptions of electronic communication; despite the experimental evidence that the neural spikes carry information on non-discrete states, they have shallow communication speed, and the spikes' timing precision matters. Furthermore, in biology, the communication channel is active, which enforces an additional power bandwidth limitation to the neural information transfer. The paper revises the notions needed to describe information transfer in technical and biological communication systems. It argues that biology uses Shannon's idea outside of its range of validity and introduces an adequate interpretation of information. In addition, the presented time-aware approach to the information theory reveals pieces of evidence for the role of processes (as opposed to states) in neural operations. The generalized information theory describes both kinds of communication, and the classic theory is the particular case of the generalized theory.

Color Variability Constrains Detection of Geometrically Perfect Mirror Symmetry

Symmetry in nature is a result of biological self-organization, driven by evolutionary processes. Detected by the visual systems of various species, from invertebrates to primates, symmetry determines survival relevant choice behaviors and supports adaptive function by reducing stimulus uncertainty. Symmetry also provides a major structural key to bio-inspired artificial vision and shape or movement simulations. In this psychophysical study, local variations in color covering the whole spectrum of visible wavelengths are compared to local variations in luminance contrast across an axis of geometrically perfect vertical mirror symmetry. The chromatic variations are found to delay response time to shape symmetry to a significantly larger extent than achromatic variations. This effect depends on the degree of variability, i.e., stimulus complexity. In both cases, we observe linear increase in response time as a function of local color variations across the vertical axis of symmetry. These results are directly explained by the difference in computational complexity between the two major (magnocellular vs. parvocellular) visual pathways involved in filtering the contrast (luminance vs. luminance and color) of the shapes. It is concluded that color variability across an axis of symmetry proves detrimental to the rapid detection of symmetry, and, presumably, other structural shape regularities. The results have implications for vision-inspired artificial intelligence and robotics exploiting functional principles of human vision for gesture and movement detection, or geometric shape simulation for recognition systems, where symmetry is often a critical property.

Bio-Inspired Control System for Fingers Actuated by Multiple SMA Actuators

Spiking neural networks are able to control with high precision the rotation and force of single-joint robotic arms when shape memory alloy wires are used for actuation. Bio-inspired robotic arms such as anthropomorphic fingers include more junctions that are actuated simultaneously. Starting from the hypothesis that the motor cortex groups the control of multiple muscles into neural synergies, this work presents for the first time an SNN structure that is able to control a series of finger motions by activation of groups of neurons that drive the corresponding actuators in sequence. The initial motion starts when a command signal is received, while the subsequent ones are initiated based on the sensors’ output. In order to increase the biological plausibility of the control system, the finger is flexed and extended by four SMA wires connected to the phalanges as the main tendons. The results show that the artificial finger that is controlled by the SNN is able to smoothly perform several motions of the human index finger while the command signal is active. To evaluate the advantages of using SNN, we compared the finger behaviours when the SMA actuators are driven by SNN, and by a microcontroller, respectively. In addition, we designed an electronic circuit that models the sensor’s output in concordance with the SNN output.