RESUMEN

Event-based neural networks are currently being explored as efficient solutions for performing AI tasks at the extreme edge. To fully exploit their potential, event-based neural networks coupled to adequate preprocessing must be investigated. Within this context, we demonstrate a 4-b-weight spiking neural network (SNN) for radar gesture recognition, achieving a state-of-the-art 93% accuracy within only four processing time steps while using only one convolutional layer and two fully connected layers. This solution consumes very little energy and area if implemented in event-based hardware, which makes it suited for embedded extreme-edge applications. In addition, we demonstrate the importance of signal preprocessing for achieving this high recognition accuracy in SNNs compared to deep neural networks (DNNs) with the same network topology and training strategy. We show that efficient preprocessing prior to the neural network is drastically more important for SNNs compared to DNNs. We also demonstrate, for the first time, that the preprocessing parameters can affect SNNs and DNNs in antagonistic ways, prohibiting the generalization of conclusions drawn from DNN design to SNNs. We demonstrate our findings by comparing the gesture recognition accuracy achieved with our SNN to a DNN with the same architecture and similar training. Unlike previously proposed neural networks for radar processing, this work enables ultralow-power radar-based gesture recognition for extreme-edge devices.

Asunto(s)

RESUMEN

We show how anomalous time reversal of stimuli and their associated responses can exist in very small connectionist models. These networks are built from dynamical toy model neurons which adhere to a minimal set of biologically plausible properties. The appearance of a "ghost" response, temporally and spatially located in between responses caused by actual stimuli, as in the phi phenomenon, is demonstrated in a similar small network, where it is caused by priming and long-distance feedforward paths. We then demonstrate that the color phi phenomenon can be present in an echo state network, a recurrent neural network, without explicitly training for the presence of the effect, such that it emerges as an artifact of the dynamical processing. Our results suggest that the color phi phenomenon might simply be a feature of the inherent dynamical and nonlinear sensory processing in the brain and in and of itself is not related to consciousness.

Asunto(s)

Asunto(s)

RESUMEN

Consciousness remains a formidable challenge. Different theories of consciousness have proposed vastly different mechanisms to account for phenomenal experience. Here, appealing to aspects of global workspace theory, higher-order theories, social theories, and predictive processing, we introduce a novel framework: the self-organizing metarerpresentational account (SOMA), in which consciousness is viewed as something that the brain learns to do. By this account, the brain continuously and unconsciously learns to redescribe its own activity to itself, so developing systems of metarepresentations that qualify target first-order representations. Thus, experiences only occur in experiencers that have learned to know they possess certain first-order states and that have learned to care more about certain states than about others. In this sense, consciousness is the brain's (unconscious, embodied, enactive, nonconceptual) theory about itself.

Asunto(s)

RESUMEN

Retriggerable and non-retriggerable monostable multivibrators are simple timers with a single characteristic, their period. Motivated by the fact that monostable multivibrators are implementable in large quantities as counters in digital programmable hardware, we set out to investigate their applicability as building blocks of artificial neural networks. We derive the nonlinear input-output firing rate relations for single multivibrator neurons as well as the equilibrium firing rate of large recurrent networks. We show that in rate-encoded monostable multivibrators networks the synaptic weights are tunable as the period ratio of connected units, and thus reconfigurable at run time in a counter-based digital implementation. This is illustrated with the task of handwritten digit recognition. Furthermore, we show in a task-independent manner that networks of monostable multivibrators are capable of nonlinear separation, when operating directly on pulse streams. Our research implies that pulse-coupled neural networks with excitable neurons showing a delayed response can perform computations even when working solely with suprathreshold pulses.

Asunto(s)

RESUMEN

We present a novel encryption scheme, wherein an encryption key is generated by two distant complex nonlinear units, forced into synchronization by a chaotic driver. The concept is sufficiently generic to be implemented on either photonic, optoelectronic or electronic platforms. The method for generating the key bitstream from the chaotic signals is reconfigurable. Although derived from a deterministic process, the obtained bit series fulfill the randomness conditions as defined by the National Institute of Standards test suite. We demonstrate the feasibility of our concept on an electronic delay oscillator circuit and test the robustness against attacks using a state-of-the-art system identification method.

RESUMEN

Reservoir computing is a paradigm in machine learning whose processing capabilities rely on the dynamical behavior of recurrent neural networks. We present a mixed analog and digital implementation of this concept with a nonlinear analog electronic circuit as a main computational unit. In our approach, the reservoir network can be replaced by a single nonlinear element with delay via time-multiplexing. We analyze the influence of noise on the performance of the system for two benchmark tasks: 1) a classification problem and 2) a chaotic time-series prediction task. Special attention is given to the role of quantization noise, which is studied by varying the resolution in the conversion interface between the analog and digital worlds.

Asunto(s)

RESUMEN

We investigate the onset of time-periodic oscillations for a system of two identical delay-coupled excitable (nonoscillatory) units. We first analyze these solutions by using asymptotic methods. The oscillations are described as relaxation oscillations exhibiting successive slow and fast changes. The analysis highlights the determinant role of the delay during the fast transition layers. We then study experimentally a system of two coupled electronic circuits that is modeled mathematically by the same delay differential equations. We obtain quantitative agreements between analytical and experimental bifurcation diagrams.