Related papers: Faster and More Accurate Sequence Alignment with S…

Pairwise alignment of DNA sequencing data is a ubiquitous task in bioinformatics and typically represents a heavy computational burden. State-of-the-art approaches to speed up this task use hashing to identify short segments (k-mers) that…

Genome sequence alignment is the core of many biological applications. The advancement of sequencing technologies produces a tremendous amount of data, making sequence alignment a critical bottleneck in bioinformatics analysis. The existing…

Neural architecture search (NAS) in expressive search spaces is a computationally hard problem, but it also holds the potential to automatically discover completely novel and performant architectures. To achieve this we need effective…

It has been proven that transfer learning provides an easy way to achieve state-of-the-art accuracies on several vision tasks by training a simple classifier on top of features obtained from pre-trained neural networks. The goal of this…

Pyrosequencing is among the emerging sequencing techniques, capable of generating upto 100,000 overlapping reads in a single run. This technique is much faster and cheaper than the existing state of the art sequencing technique such as…

Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural network architectures designed for image classification as…

DNA sequence classification is a fundamental task in computational biology with vast implications for applications such as disease prevention and drug design. Therefore, fast high-quality sequence classifiers are significantly important.…

Spiking Neural Networks (SNNs) offer a promising solution to the problem of increasing computational and energy requirements for modern Machine Learning (ML) applications. Due to their unique data representation choice of using spikes and…

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the…

GNAS (Graph Neural Architecture Search) has demonstrated great effectiveness in automatically designing the optimal graph neural architectures for multiple downstream tasks, such as node classification and link prediction. However, most…

Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…

With the advent of Next-Generation (NG) sequencing, it has become possible to sequence an entire genome quickly and inexpensively. However, in some experiments one only needs to extract and assembly a portion of the sequence reads, for…

Spiking neural networks (SNNs) promise energy-efficient computation by mimicking biological neural dynamics, yet existing plasticity rules focus on isolated spike pairs and fail to leverage the synchronous activity patterns that drive…

A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. However, RNNs are fundamentally unable to randomly access…

Spiking Neural Networks (SNNs) have been attached great importance due to their biological plausibility and high energy-efficiency on neuromorphic chips. As these chips are usually resource-constrained, the compression of SNNs is thus…

Bayesian neural networks (BNNs) require scalable sampling algorithms to approximate posterior distributions over parameters. Existing stochastic gradient Markov Chain Monte Carlo (SGMCMC) methods are highly sensitive to the choice of…

Approximate Nearest Neighbor Search (ANNS) is a fundamental operation in vector databases, enabling efficient similarity search in high-dimensional spaces. While dense ANNS has been optimized using specialized hardware accelerators, sparse…

We recently proposed the STiDi-BP algorithm, which avoids backward recursive gradient computation, for training multi-layer spiking neural networks (SNNs) with single-spike-based temporal coding. The algorithm employs a linear approximation…

Due to a high heterogeneity in pose and size and to a limited number of available data, segmentation of pediatric images is challenging for deep learning methods. In this work, we propose a new CNN architecture that is pose and scale…

Dedicated accelerator hardware has become essential for processing AI-based workloads, leading to the rise of novel accelerator architectures. Furthermore, fundamental differences in memory architecture and parallelism have made these…