Trevor Bihl

Taylor W. Webb, Shuhao Fu, Trevor Bihl et al.

Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require extensive direct training on visual reasoning tasks, and yield limited generalization to problems with novel content. In contrast, a long tradition of research in cognitive science has focused on elucidating the computational principles underlying human analogical reasoning; however, this work has generally relied on manually constructed representations. Here we present visiPAM (visual Probabilistic Analogical Mapping), a model of visual reasoning that synthesizes these two approaches. VisiPAM employs learned representations derived directly from naturalistic visual inputs, coupled with a similarity-based mapping operation derived from cognitive theories of human reasoning. We show that without any direct training, visiPAM outperforms a state-of-the-art deep learning model on an analogical mapping task. In addition, visiPAM closely matches the pattern of human performance on a novel task involving mapping of 3D objects across disparate categories.

Alex Vicente-Sola, Davide L. Manna, Paul Kirkland et al.

Spiking Neural Networks (SNN) are characterised by their unique temporal dynamics, but the properties and advantages of such computations are still not well understood. In order to provide answers, in this work we demonstrate how Spiking neurons can enable temporal feature extraction in feed-forward neural networks without the need for recurrent synapses, and how recurrent SNNs can achieve comparable results to LSTM with a smaller number of parameters. This shows how their bio-inspired computing principles can be successfully exploited beyond energy efficiency gains and evidences their differences with respect to conventional artificial neural networks. These results are obtained through a new task, DVS-Gesture-Chain (DVS-GC), which allows, for the first time, to evaluate the perception of temporal dependencies in a real event-based action recognition dataset. Our study proves how the widely used DVS Gesture benchmark can be solved by networks without temporal feature extraction when its events are accumulated in frames, unlike the new DVS-GC which demands an understanding of the order in which events happen. Furthermore, this setup allowed us to reveal the role of the leakage rate in spiking neurons for temporal processing tasks and demonstrated the benefits of "hard reset" mechanisms. Additionally, we also show how time-dependent weights and normalization can lead to understanding order by means of temporal attention.

Davide Liberato Manna, Alex Vicente Sola, Paul Kirkland et al.

Spiking neural networks (SNNs) are largely inspired by biology and neuroscience and leverage ideas and theories to create fast and efficient learning systems. Spiking neuron models are adopted as core processing units in neuromorphic systems because they enable event-based processing. The integrate-and-fire (I&F) models are often adopted, with the simple Leaky I&F (LIF) being the most used. The reason for adopting such models is their efficiency and/or biological plausibility. Nevertheless, rigorous justification for adopting LIF over other neuron models for use in artificial learning systems has not yet been studied. This work considers various neuron models in the literature and then selects computational neuron models that are single-variable, efficient, and display different types of complexities. From this selection, we make a comparative study of three simple I&F neuron models, namely the LIF, the Quadratic I&F (QIF) and the Exponential I&F (EIF), to understand whether the use of more complex models increases the performance of the system and whether the choice of a neuron model can be directed by the task to be completed. Neuron models are tested within an SNN trained with Spike-Timing Dependent Plasticity (STDP) on a classification task on the N-MNIST and DVS Gestures datasets. Experimental results reveal that more complex neurons manifest the same ability as simpler ones to achieve high levels of accuracy on a simple dataset (N-MNIST), albeit requiring comparably more hyper-parameter tuning. However, when the data possess richer Spatio-temporal features, the QIF and EIF neuron models steadily achieve better results. This suggests that accurately selecting the model based on the richness of the feature spectrum of the data could improve the whole system's performance. Finally, the code implementing the spiking neurons in the SpykeTorch framework is made publicly available.

Marco Cominelli, Francesco Gringoli, Lance M. Kaplan et al.

Wi-Fi devices, akin to passive radars, can discern human activities within indoor settings due to the human body's interaction with electromagnetic signals. Current Wi-Fi sensing applications predominantly employ data-driven learning techniques to associate the fluctuations in the physical properties of the communication channel with the human activity causing them. However, these techniques often lack the desired flexibility and transparency. This paper introduces DeepProbHAR, a neuro-symbolic architecture for Wi-Fi sensing, providing initial evidence that Wi-Fi signals can differentiate between simple movements, such as leg or arm movements, which are integral to human activities like running or walking. The neuro-symbolic approach affords gathering such evidence without needing additional specialised data collection or labelling. The training of DeepProbHAR is facilitated by declarative domain knowledge obtained from a camera feed and by fusing signals from various antennas of the Wi-Fi receivers. DeepProbHAR achieves results comparable to the state-of-the-art in human activity recognition. Moreover, as a by-product of the learning process, DeepProbHAR generates specialised classifiers for simple movements that match the accuracy of models trained on finely labelled datasets, which would be particularly costly.

Ye Yue, Marc Baltes, Nidal Abujahar et al.

Over the past decade, artificial neural networks (ANNs) have made tremendous advances, in part due to the increased availability of annotated data. However, ANNs typically require significant power and memory consumptions to reach their full potential. Spiking neural networks (SNNs) have recently emerged as a low-power alternative to ANNs due to their sparsity nature. SNN, however, are not as easy to train as ANNs. In this work, we propose a hybrid SNN training scheme and apply it to segment human hippocampi from magnetic resonance images. Our approach takes ANN-SNN conversion as an initialization step and relies on spike-based backpropagation to fine-tune the network. Compared with the conversion and direct training solutions, our method has advantages in both segmentation accuracy and training efficiency. Experiments demonstrate the effectiveness of our model in achieving the design goals.

Alex Vicente-Sola, Davide L. Manna, Paul Kirkland et al.

Spiking neural networks (SNNs) have become an interesting alternative to conventional artificial neural networks (ANN) thanks to their temporal processing capabilities and energy efficient implementations in neuromorphic hardware. However the challenges involved in training SNNs have limited their performance in terms of accuracy and thus their applications. Improving learning algorithms and neural architectures for a more accurate feature extraction is therefore one of the current priorities in SNN research. In this paper we present a study on the key components of modern spiking architectures. We design a spiking version of the successful residual network architecture and provide an in-depth study on the possible implementations of spiking residual connections. This study shows how, depending on the use case, the optimal residual connection implementation may vary. Additionally, we empirically compare different techniques in image classification datasets taken from the best performing networks. Our results provide a state of the art guide to SNN design, which allows to make informed choices when trying to build the optimal visual feature extractor. Finally, our network outperforms previous SNN architectures in CIFAR-10 (94.14%) and CIFAR-100 (74.65%) datasets and matches the state of the art in DVS-CIFAR10 (72.98%), with less parameters than the previous state of the art and without the need for ANN-SNN conversion. Code available at https://github.com/VicenteAlex/Spiking_ResNet

Alessandro Pagani, Marco Cominelli, Liying Han et al.

This paper presents a preliminary analysis of the ability of Chronos foundation model to process and internally represent frequency domain information. Foundation models that process time-series data offer practitioners a unified architecture capable of learning generic temporal representations across diverse tasks and domains, reducing the need for task-specific feature engineering and enabling transfer across signal modalities. Despite their growing adoption, the extent to which such models encode fundamental signal properties remains insufficiently characterised. We address this gap by analysing Chronos under controlled conditions, starting from the simplest class of signals: discrete sinusoids generated at fixed frequencies. Using lightweight online minimum description length probes applied to the decoder architecture, we test for the presence and separability of frequency information in the model's internal representations. The results provide insight into how frequential content is captured across the frequency spectrum and highlight regimes in which representation quality may degrade or require particular care. These findings offer practical guidance for users of Chronos in signal processing and information fusion contexts, and contribute to ongoing efforts to improve the interpretability and evaluation of foundation models for temporal data.

Luca Cotti, Luca Lavazza, Marco Cominelli et al.

We address Human Activity Recognition (HAR) utilizing Wi-Fi Channel State Information (CSI) under the joint requirements of causal interpretability, symbolic controllability, and direct operation on high-dimensional raw signals. Deep neural models achieve strong predictive performance on CSI-based HAR (CHAR), yet rely on continuous latent representations that are opaque and difficult to modify; purely symbolic approaches, in contrast, cannot process raw CSI streams. We propose a fully automatic and strictly decoupled pipeline in which CSI magnitude windows are compressed by a categorical variational autoencoder with Gumbel-Softmax latent variables under a capacity-controlled objective, yielding a compact discrete representation. The encoder is then frozen and used as a deterministic mapping to one-hot latent trajectories. Causal discovery is performed on these trajectories to estimate class-conditional temporal dependency graphs. Statistically supported lagged dependencies are translated into Linear Temporal Logic (LTL) rules, producing a fully symbolic and deterministic classifier based solely on rule evaluation and aggregation, without any learned discriminative head. Because rules are defined over discrete latent variables, antenna-specific rule sets can in principle be combined at the symbolic level, enabling structured multi-antenna fusion without retraining the encoder. Results from CHAR Latent Temporal Rule Extraction (CHARL-TRE) indicate competitive performance while preserving explicit temporal and causal structure, showing that deterministic symbolic classification grounded in unsupervised discrete latent representations constitutes a viable alternative to end-to-end black-box models for wireless HAR.

Shuhao Fu, Andrew Jun Lee, Anna Wang et al.

The visual world is fundamentally compositional. Visual scenes are defined by the composition of objects and their relations. Hence, it is essential for computer vision systems to reflect and exploit this compositionality to achieve robust and generalizable scene understanding. While major strides have been made toward the development of general-purpose, multimodal generative models, including both text-to-image models and multimodal vision-language models, it remains unclear whether these systems are capable of accurately generating and interpreting scenes involving the composition of multiple objects and relations. In this work, we present an evaluation of the compositional visual processing capabilities in the current generation of text-to-image (DALL-E 3) and multimodal vision-language models (GPT-4V, GPT-4o, Claude Sonnet 3.5, QWEN2-VL-72B, and InternVL2.5-38B), and compare the performance of these systems to human participants. The results suggest that these systems display some ability to solve compositional and relational tasks, showing notable improvements over the previous generation of multimodal models, but with performance nevertheless well below the level of human participants, particularly for more complex scenes involving many ($>5$) objects and multiple relations. These results highlight the need for further progress toward compositional understanding of visual scenes.

Andrew Jun Lee, Taylor Webb, Trevor Bihl et al.

The ability to learn new visual concepts from limited examples is a hallmark of human cognition. While traditional category learning models represent each example as an unstructured feature vector, compositional concept learning is thought to depend on (1) structured representations of examples (e.g., directed graphs consisting of objects and their relations) and (2) the identification of shared relational structure across examples through analogical mapping. Here, we introduce Probabilistic Schema Induction (PSI), a prototype model that employs deep learning to perform analogical mapping over structured representations of only a handful of examples, forming a compositional concept called a schema. In doing so, PSI relies on a novel conception of similarity that weighs object-level similarity and relational similarity, as well as a mechanism for amplifying relations relevant to classification, analogous to selective attention parameters in traditional models. We show that PSI produces human-like learning performance and outperforms two controls: a prototype model that uses unstructured feature vectors extracted from a deep learning model, and a variant of PSI with weaker structured representations. Notably, we find that PSI's human-like performance is driven by an adaptive strategy that increases relational similarity over object-level similarity and upweights the contribution of relations that distinguish classes. These findings suggest that structured representations and analogical mapping are critical to modeling rapid human-like learning of compositional visual concepts, and demonstrate how deep learning can be leveraged to create psychological models.