Related papers: Modeling Retinal Ganglion Cells with Neural Differ…
Modelling the mass distributions of strong gravitational lenses is often necessary to use them as astrophysical and cosmological probes. With the high number of lens systems ($>10^5$) expected from upcoming surveys, it is timely to explore…
This study presents a new deep learning framework, combining Spatio-Temporal Graph Convolutional Network (STGCN) with a Large Language Model (LLM), for bike demand forecasting. Addressing challenges in transforming discrete datasets and…
We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a…
In speech enhancement, achieving state-of-the-art (SotA) performance while adhering to the computational constraints on edge devices remains a formidable challenge. Networks integrating stacked temporal and spectral modelling effectively…
Real-world visual recognition problems often exhibit long-tailed distributions, where the amount of data for learning in different categories shows significant imbalance. Standard classification models learned on such data distribution…
Recently, foundation models have been introduced demonstrating various tasks in the field of computer vision. These models such as Segment Anything Model (SAM) are generalized models trained using huge datasets. Currently, ongoing research…
Contrastive learning has been proved to be a promising technique for image-level representation learning from unlabeled data. Many existing works have demonstrated improved results by applying contrastive learning in classification and…
Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…
Convolutional neural networks are nowadays witnessing a major success in different pattern recognition problems. These learning models were basically designed to handle vectorial data such as images but their extension to non-vectorial and…
There exist several data-driven approaches that enable us model time series data including traditional regression-based modeling approaches (i.e., ARIMA). Recently, deep learning techniques have been introduced and explored in the context…
We present a simple mathematical model for the mammalian low visual pathway, taking into account its key elements: retina, lateral geniculate nucleus (LGN), primary visual cortex (V1). The analogies between the cortical level of the visual…
Radar systems are increasingly favored for medical applications because they provide non-intrusive monitoring with high privacy and robustness to lighting conditions. However, existing research typically relies on single-domain radar…
Despite the utility of neural networks (NNs) for astronomical time-series classification, the proliferation of learning architectures applied to diverse datasets has thus far hampered a direct intercomparison of different approaches. Here…
Cortical networks are strongly recurrent, and neurons have intrinsic temporal dynamics. This sets them apart from deep feed-forward networks. Despite the tremendous progress in the application of feed-forward networks and their theoretical…
Long Short-Term Memory (LSTM) is a prominent recurrent neural network for extracting dependencies from sequential data such as time-series and multi-view data, having achieved impressive results for different visual recognition tasks. A…
Convolutional Neural Networks experience catastrophic forgetting when optimized on a sequence of learning problems: as they meet the objective of the current training examples, their performance on previous tasks drops drastically. In this…
The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves…
Continual learning (CL) for Foundation Models (FMs) is an essential yet underexplored challenge, especially in Federated Continual Learning (FCL), where each client learns from a private, evolving task stream under strict data and…
The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all candidates due to computational constraints. Despite the recent…
Neural population activity exhibits complex, nonlinear dynamics, varying in time, over trials, and across experimental conditions. Here, we develop Conditionally Linear Dynamical System (CLDS) models as a general-purpose method to…