Related papers: An Optimized Recurrent Unit for Ultra-Low-Power Ke…
Audio-visual navigation represents a significant area of research in which intelligent agents utilize egocentric visual and auditory perceptions to identify audio targets. Conventional navigation methodologies typically adopt a staged…
Objective: To allow efficient learning using the Recurrent Inference Machine (RIM) for image reconstruction whereas not being strictly dependent on the training data distribution so that unseen modalities and pathologies are still…
Convolutional neural network (CNN) and recurrent neural network (RNN) models have become the mainstream methods for relation classification. We propose a unified architecture, which exploits the advantages of CNN and RNN simultaneously, to…
We propose a single neural network architecture for two tasks: on-line keyword spotting and voice activity detection. We develop novel inference algorithms for an end-to-end Recurrent Neural Network trained with the Connectionist Temporal…
Movement control of artificial limbs has made big advances in recent years. New sensor and control technology enhanced the functionality and usefulness of artificial limbs to the point that complex movements, such as grasping, can be…
Environmental audio tagging is a newly proposed task to predict the presence or absence of a specific audio event in a chunk. Deep neural network (DNN) based methods have been successfully adopted for predicting the audio tags in the…
Real-time classification of Electromyography signals is the most challenging part of controlling a prosthetic hand. Achieving a high classification accuracy of EMG signals in a short delay time is still challenging. Recurrent neural…
Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values. In time series prediction and other related tasks, it has been noted that missing…
Recurrent neural network (RNN), as a powerful contextual dependency modeling framework, has been widely applied to scene labeling problems. However, this work shows that directly applying traditional RNN architectures, which unfolds a 2D…
Speech enhancement plays an essential role in improving the quality of speech signals in noisy environments. This paper investigates the efficacy of integrating Bidirectional Gated Recurrent Units (BGRU) and Transformer models for speech…
Manual endoscopic submucosal dissection (ESD) is technically demanding, and existing single-segment robotic tools offer limited dexterity. These limitations motivate the development of more advanced solutions. To address this, DESectBot, a…
This paper elucidates a model for acoustic single and multi-tone classification in resource constrained edge devices. The proposed model is of State-of-the-art Fast Accurate Stable Tiny Gated Recurrent Neural Network. This model has…
We introduce the use of a Gated Recurrent Unit (GRU) for influenza prediction at the state- and city-level in the US, and experiment with the inclusion of real-time flu-related Internet search data. We find that a GRU has lower prediction…
The cost aggregation strategy shows a crucial role in learning-based stereo matching tasks, where 3D convolutional filters obtain state of the art but require intensive computation resources, while 2D operations need less GPU memory but are…
Gated Linear Units (GLUs) have become essential components in the feed-forward networks of state-of-the-art Large Language Models (LLMs). However, they require twice as many memory reads compared to feed-forward layers without gating, due…
Recently deep learning based Natural Language Processing (NLP) models have shown great potential in the modeling of source code. However, a major limitation of these approaches is that they take source code as simple tokens of text and…
We report the results of our classification-based machine translation model, built upon the framework of a recurrent neural network using gated recurrent units. Unlike other RNN models that attempt to maximize the overall conditional log…
This machine learning study investigates a lowcost edge device integrated with an embedded system having computer vision and resulting in an improved performance in inferencing time and precision of object detection and classification. A…
This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them…
Language Identification, being an important aspect of Automatic Speaker Recognition has had many changes and new approaches to ameliorate performance over the last decade. We compare the performance of using audio spectrum in the log scale…