Brain-like algorithms are attractive and emerging alternatives to classical deep learning methods for use in various machine learning applications. Brain-like systems can feature local learning rules, both unsupervised/semi-supervised learning and different types of plasticity (structural/synaptic), allowing them to potentially be faster and more energy-efficient than traditional machine learning alternatives. Among the more salient brain-like algorithms are Bayesian Confidence Propagation Neural Networks (BCPNNs). BCPNN is an important tool for both machine learning and computational neuroscience research, and recent work shows that BCPNN can reach state-of-the-art performance in tasks such as learning and memory recall compared to other models. Unfortunately, BCPNN is primarily executed on slow general-purpose processors (CPUs) or power-hungry graphics processing units (GPUs), reducing the applicability of using BCPNN in Edge systems, among others. In this work, we design a reconfigurable stream-based accelerator for BCPNN using Field-Programmable Gate Arrays (FPGA) using Xilinx Vitis High-Level Synthesis (HLS) flow. Furthermore, we model our accelerator’s performance using first principles, and we empirically show that our proposed accelerator (full-featured kernel non-structural plasticity) is between 1.3x - 5.3x faster than an Nvidia A100 GPU while at the same time consuming between 2.62x - 3.19x less power and 5.8x - 16.5x less energy without any degradation in performance.

Neural networks that can capture key principles underlying brain computation offer exciting new opportunities for developing artificial intelligence and brain-like computing algorithms. Such networks remain biologically plausible while leveraging localized forms of synaptic learning rules and modular network architecture found in the neocortex. Compared to backprop-driven deep learning approches, they provide more suitable models for deployment of neuromorphic hardware and have greater potential for scalability on large-scale computing clusters. The development of such brain-like neural networks depends on having a learning procedure that can build effective internal representations from data. In this work, we introduce and evaluate a brain-like neural network model capable of unsupervised representation learning. It builds on the Bayesian Confidence Propagation Neural Network (BCPNN), which has earlier been implemented as abstract as well as biophysically detailed recurrent attractor neural networks explaining various cortical associative memory phenomena. Here we developed a feedforward BCPNN model to perform representation learning by incorporating a range of brainlike attributes derived from neocortical circuits such as cortical columns, divisive normalization, Hebbian synaptic plasticity, structural plasticity, sparse activity, and sparse patchy connectivity. The model was tested on a diverse set of popular machine learning benchmarks: grayscale images (MNIST, F-MNIST), RGB natural images (SVHN, CIFAR-10), QSAR (MUV, HIV), and malware detection (EMBER). The performance of the model when using a linear classifier to predict the class labels fared competitively with conventional multi-layer perceptrons and other state-of-the-art brain-like neural networks.

Naming common odors is a surprisingly difficult task: Odors are frequently misnamed. Little is known about the linguistic properties of odor misnamings. We test whether odor misnamings of old adults carry information about olfactory perception and its connection to lexical-semantic processing. We analyze the olfactory-semantic content of odor source naming failures in a large sample of older adults in Sweden (n = 2479; age 58-100 years). We investigate whether linguistic factors and semantic proximity to the target odor name predict how odors are misnamed, and how these factors relate to overall odor identification performance. We also explore the primary semantic dimensions along which misnamings are distributed. We find that odor misnamings consist of surprisingly many vague and unspecific terms, such as category names (e.g., fruit) or abstract or evaluative terms (e.g., sweet). Odor misnamings are often strongly associated with the correct name, capturing properties such as its category or other abstract features. People are also biased toward misnaming odors with high-frequency terms that are associated with olfaction or gustation. Linguistic properties of odor misnamings and their semantic proximity to the target odor name predict odor identification performance, suggesting that linguistic processing facilitates odor identification. Further, odor misnamings constitute an olfactory-semantic space that is similar to the olfactory vocabulary of English. This space is primarily differentiated along pleasantness, edibility, and concreteness dimensions. Odor naming failures thus contain plenty of information about semantic odor knowledge.

Beta oscillations are linked to the control of goal-directed processing of sensory information and the timing of motor output. Recent evidence demonstrates they are not sustained but organized into intermittent high-power bursts mediating timely functional inhibition. This implies there is a considerable moment-tomoment variation in the neural dynamics supporting cognition. Beta bursts thus offer new opportunities for studying how sensory inputs are selectively processed, reshaped by inhibitory cognitive operations and ultimately result in motor actions. Recent method advances reveal diversity in beta bursts that provide deeper insights into their function and the underlying neural circuit activity motifs. We propose that brain-wide, spatiotemporal patterns of beta bursting reflect various cognitive operations and that their dynamics reveal nonlinear aspects of cortical processing.

This paper addresses the growing application of data-driven approaches within the Private Equity (PE) industry, particularly in sourcing investment targets (i.e., companies) for Venture Capital (VC) and Growth Capital (GC). We present a comprehensive review of the relevant approaches and propose a novel approach leveraging a Transformer-based Multivariate Time Series Classifier (TMTSC) for predicting the success likelihood of any candidate company. The objective of our research is to optimize sourcing performance for VC and GC investments by formally defining the sourcing problem as a multivariate time series classification task. We consecutively introduce the key components of our implementation which collectively contribute to the successful application of TMTSC in VC/GC sourcing: input features, model architecture, optimization target, and investor-centric data processing. Our extensive experiments on two real-world investment tasks, benchmarked towards three popular baselines, demonstrate the effectiveness of our approach in improving decision making within the VC and GC industry.

Multiple neural mechanisms underlying gating to working memory have been proposed with divergent results obtained in human and animal studies. Previous findings from non-human primates suggest prefrontal beta frequency bursts as a correlate of transient inhibition during selective encoding. Human studies instead suggest a similar role for sensory alpha power fluctuations. To cast light on these discrepancies we employed a sequential working memory task with distractors for human participants. In particular, we examined their whole-brain electrophysiological activity in both alpha and beta bands with the same single-trial burst analysis earlier performed on non-human primates. Our results reconcile earlier findings by demonstrating that both alpha and beta bursts in humans correlate with the filtering and control of memory items, but with region and task-specific differences between the two rhythms. Occipital beta burst patterns were selectively modulated during the transition from sensory processing to memory retention whereas prefrontal and parietal beta bursts tracked sequence order and were proactively upregulated prior to upcoming target encoding. Occipital alpha bursts instead increased during the actual presentation of unwanted sensory stimuli. Source reconstruction additionally suggested the involvement of striatal and thalamic alpha and beta. Thus, specific whole-brain burst patterns correlate with different aspects of working memory control.

The random utility model (RUM) is a fundamental notion in studies of human decision-making. However, RUM relies on the calibration of its choice function's weight parameter, usually interpreted as a rationality parameter, resulting in a case-dependence that undermines both interpretability and predictability of choices across experimental settings. We addressed this limitation by normalizing utilities in RUM and deriving a new choice parameter β, independent of case-specific prospects. Drawing from a novel interpretation of β in terms of the lowest perceived probability of unlikely events, we conducted an experimental survey in Swedish universities to infer β distributions, capturing the variability of probability perception among decision-makers. We tested these statistical models for β on two independent datasets exploring the framing effect. The results showed that the predictions align with the observed experimental data (Pearson's correlation greater than 94%), thereby indicating that the novel characterization of the choice parameter strengthens the predictive capabilities of RUM.

Time Series Representation Learning (TSRL) focuses on generating informative representations for various Time Series (TS) modeling tasks. Traditional Self-Supervised Learning (SSL) methods in TSRL fall into four main categories: reconstructive, adversarial, contrastive, and predictive, each with a common challenge of sensitivity to noise and intricate data nuances. Recently, diffusion-based methods have shown advanced generative capabilities. However, they primarily target specific application scenarios like imputation and forecasting, leaving a gap in leveraging diffusion models for generic TSRL. Our work, Time Series Diffusion Embedding (TSDE), bridges this gap as the first diffusion-based SSL TSRL approach. TSDE segments TS data into observed and masked parts using an Imputation-Interpolation-Forecasting (IIF) mask. It applies a trainable embedding function, featuring dual-orthogonal Transformer encoders with a crossover mechanism, to the observed part. We train a reverse diffusion process conditioned on the embeddings, designed to predict noise added to the masked part. Extensive experiments demonstrate TSDE's superiority in imputation, interpolation, forecasting, anomaly detection, classification, and clustering. We also conduct an ablation study, present embedding visualizations, and compare inference speed, further substantiating TSDE's efficiency and validity in learning representations of TS data.

Networks of interconnected neurons communicating through spiking signals offer the bedrock of neural computations. Our brain's spiking neural networks have the computational capacity to achieve complex pattern recognition and cognitive functions effortlessly. However, solving real-world problems with artificial spiking neural networks (SNNs) has proved to be difficult for a variety of reasons. Crucially, scaling SNNs to large networks and processing large-scale real-world datasets have been challenging, especially when compared to their non-spiking deep learning counterparts. The critical operation that is needed of SNNs is the ability to learn distributed representations from data and use these representations for perceptual, cognitive and memory operations. In this work, we introduce a novel SNN that performs unsupervised representation learning and associative memory operations leveraging Hebbian synaptic and activity-dependent structural plasticity coupled with neuron-units modelled as Poisson spike generators with sparse firing (similar to 1 Hz mean and similar to 100 Hz maximum firing rate). Crucially, the architecture of our model derives from the neocortical columnar organization and combines feedforward projections for learning hidden representations and recurrent projections for forming associative memories. We evaluated the model on properties relevant for attractor-based associative memories such as pattern completion, perceptual rivalry, distortion resistance, and prototype extraction.

According to the efficient coding hypothesis, sensory neurons are adapted to provide maximal information about the environment, given some biophysical constraints. In early visual areas, stimulus-induced modulations of neural activity (or tunings) are predominantly single-peaked. However, periodic tuning, as exhibited by grid cells, has been linked to a significant increase in decoding performance. Does this imply that the tuning curves in early visual areas are sub-optimal? We argue that the time scale at which neurons encode information is imperative to understand the advantages of single-peaked and periodic tuning curves, respectively. Here, we show that the possibility of catastrophic (large) errors creates a trade-off between decoding time and decoding ability. We investigate how decoding time and stimulus dimensionality affect the optimal shape of tuning curves for removing catastrophic errors. In particular, we focus on the spatial periods of the tuning curves for a class of circular tuning curves. We show an overall trend for minimal decoding time to increase with increasing Fisher information, implying a trade-off between accuracy and speed. This trade-off is reinforced whenever the stimulus dimensionality is high, or there is ongoing activity. Thus, given constraints on processing speed, we present normative arguments for the existence of the single-peaked tuning organization observed in early visual areas.