Alexander Hadjiivanov

Event cameras, as novel bio-inspired neuromorphic sensors, detect per-pixel brightness changes asynchronously. Despite their growing popularity in various applications, their potential in X-ray imaging remains largely unexplored. Synchrotron-based X-ray imaging plays a significant role in various fields of science, technology and medicine. However, time-resolved imaging still faces several challenges in achieving higher sampling rates and managing the substantial data volume. Here, we introduce an inline dual-camera setup, which leverages a high-speed CMOS camera and an event camera, aiming to temporally super-resolve the sampled frame data using sparse events. To process the data, frames and events are first aligned pixel-by-pixel using feature matching, and then used to train a deep-learning neural network. This network effectively integrates the two modalities to reconstruct the intermediate frames, achieving up to a 6-fold temporal upsampling. Our work demonstrates an event-guided temporal super-resolution approach in the X-ray imaging domain, which unlocks possibilities for future time-resolved experiments.

The organizers of the third Space Optimization Competition (SpOC)¹ give a brief overview of the competition. We lay out the timeline and discuss administrative decisions. As was common in previous editions, the competition consists of three problems. We present them swiftly and provide their scientific background and motivation.

In this study, we build upon a previously proposed neuroevolution framework to evolve deep convolutional models. Specifically, the genome encoding and the crossover operator are extended to make them applicable to layered networks. We also propose a convolutional layer layout which allows kernels of different shapes and sizes to coexist within the same layer, and present an argument as to why this may be beneficial. The proposed layout enables the size and shape of individual kernels within a convolutional layer to be evolved with a corresponding new mutation operator. The proposed framework employs a hybrid optimisation strategy involving structural changes through epigenetic evolution and weight update through backpropagation in a population-based setting. Experiments on several image classification benchmarks demonstrate that the crossover operator is sufficiently robust to produce increasingly performant offspring even when the parents are trained on only a small random subset of the training dataset in each epoch, thus providing direct confirmation that learned features and behaviour can be successfully transferred from parent networks to offspring in the next generation.

This paper introduces a speciation principle for neuroevolution where evolving networks are grouped into species based on the number of hidden neurons, which is indicative of the complexity of the search space. This speciation principle is indivisibly coupled with a novel genotype representation which is characterised by zero genome redundancy, high resilience to bloat, explicit marking of recurrent connections, as well as an efficient and reproducible stack-based evaluation procedure for networks with arbitrary topology. Furthermore, the proposed speciation principle is employed in several techniques designed to promote and preserve diversity within species and in the ecosystem as a whole. The competitive performance of the proposed framework, named Cortex, is demonstrated through experiments. A highly customisable software platform which implements the concepts proposed in this study is also introduced in the hope that it will serve as a useful and reliable tool for experimentation in the field of neuroevolution.

This paper presents a biologically plausible method for converting real-valued input into spike trains for processing with spiking neural networks. The proposed method mimics the adaptive behaviour of retinal ganglion cells and allows input neurons to adapt their response to changes in the statistics of the input. Thus, rather than passively receiving values and forwarding them to the hidden and output layers, the input layer acts as a self-regulating filter which emphasises deviations from the average while allowing the input neurons to become effectively desensitised to the average itself. Another merit of the proposed method is that it requires only one input neuron per variable, rather than an entire population of neurons as in the case of the commonly used conversion method based on Gaussian receptive fields. In addition, since the statistics of the input emerge naturally over time, it becomes unnecessary to pre-process the data before feeding it to the network. This enables spiking neural networks to process raw, non-normalised streaming data. A proof-of-concept experiment is performed to demonstrate that the proposed method operates as expected.