MLINFO COLLECTION
Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal cortex, is known to modulate working memory and…
We study whether the coordinate dependence of the improved Self-Organizing Migrating Algorithm (iSOMA) can be reduced while retaining its inexpensive leader-directed migration mechanism. We introduce…
We propose a new spiking neural network (SNN) design to process static images and event streams using time-to-first-spike (TTFS) latencies. Our key research question is which architectural choices…
Clinical scalp electroencephalography (EEG) offers a noninvasive window into neural dynamics of neuropsychiatric disorders. However, discriminative deep models often lack anatomically indexed…
Hardware accelerators based on physical dynamical systems offer an attractive route toward energy-efficient reinforcement learning applications. However, their scalability is challenging because it…
Sensor networks and radars can deliver signals as organized sets, e.g. ordered signals, signals describing range cells within a grid or signals perceived as graph nodes.
Adam and its variants dominate neural network training, but a single run only reveals whether a configuration works well after most of its budget is spent, a poor fit for hyperparameter or…
A critical analysis of contemporary approaches to the study of conscious states. The review focuses on methods of classification, clustering, modeling of brain states under anesthesia and…
We study the knowledge matrix of a trained feedforward network as a higher representation of its inputs. A network is a pair $(W,f)$, a thin representation $W$ of its quiver and an activation $f$;…
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
A central aim of neuromorphic computing is to provide a viable alternative to highly energy-intensive Transformer-based AI. However, efficient alternatives struggle to capture the set of qualities…
Convolutional EEG decoders are trained at a fixed width, usually set by their authors on other data. Growing methods add neurons during training where the loss could decrease the most, but whether…
Production scheduling requires realistic models that reflect operational constraints and efficient methods that balance competing goals. Putting these methods into use also requires data integration,…
Continuous-time sensing and monitoring with timely and accurate decision-making are critical for many real-world applications. In healthcare monitoring systems, physiological signals are often…
Spiking Vision Transformers (SViTs) are developed as an energy-efficient alternative to conventional ViTs for computer vision tasks at the edge. However, huge parameter counts and complex multi-head…
Spiking-Mamba hybrids reach strong accuracy on event-based vision, but existing designs often require tens of millions of parameters. Much of that cost comes from how the spiking front-end is…
As AI models grow in size and usage, their energy demands increase dramatically, raising sustainability and economic concerns. Neuromorphic hardware, inspired by the energy efficiency of the brain,…
Continual Graph Learning (CGL) aims to incrementally learn from graph-structured data while preserving knowledge acquired from previous tasks. A major challenge in this setting is catastrophic…
We introduce Distance-Residual Physics-Informed Neural Networks (DR-PINNs), a physics-informed learning framework for approximating solutions of ordinary and partial differential inclusions (DIs),…
Biological neurons exhibit diverse firing dynamics that enable adaptive and stimulus-dependent signalling, yet reproducing these dynamics in hardware has remained an enduring challenge. In this work,…
Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid outputs, plain stochastic gradient descent can…
Artificial neural networks (ANNs) usually represent neural transmission with fixed trainable weights during a training batch, which omits short-term changes in synaptic efficacy. In addition, the…
Training quantum neural networks (QNNs) on near-term hardware remains hampered by two compounding difficulties: the exponential vanishing of gradient variance known as the barren plateau, and the…
Neurons in the visual system are selective for specific spatial and temporal stimulus features, described by their \emph{receptive field}. Estimating one means a coefficient per pixel per time bin…