Related papers: Powerful and Extensible WFST Framework for RNN-Tra…

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very…

Recurrent neural networks (RNNs), particularly LSTMs, are effective for time-series tasks like sentiment analysis and short-term stock prediction. However, their computational complexity poses challenges for real-time deployment in resource…

This paper proposes robust nonlinear transform coding (Robust-NTC), a generalizable digital joint source-channel coding (JSCC) framework that couples variational latent modeling with channel-adaptive transmission. Unlike learning-based JSCC…

Popular solutions to Named Entity Recognition (NER) include conditional random fields, sequence-to-sequence models, or utilizing the question-answering framework. However, they are not suitable for nested and overlapping spans with large…

We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…

This paper proposes a Fast Graph Convolutional Neural Network (FGRNN) architecture to predict sequences with an underlying graph structure. The proposed architecture addresses the limitations of the standard recurrent neural network (RNN),…

We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs. The advantages of our framework are two-fold; 1) it transforms various…

This paper theoretically and experimentally investigates frequency-tuned and impedance-tuned wireless non-radiative power transfer (WNPT) systems. Closed-form expressions for the efficiencies of both systems, as a function of frequency and…

While Connectionist Temporal Classification (CTC) models deliver state-of-the-art accuracy in automated speech recognition (ASR) pipelines, their performance has been limited by CPU-based beam search decoding. We introduce a GPU-accelerated…

Data-dependent secondary transforms, which aim to decorrelate coefficients of a separable primary transform, can improve residual coding efficiency; however, their deployment is often constrained by computational complexity. Recent video…

Health prediction is crucial for ensuring reliability, minimizing downtime, and optimizing maintenance in industrial systems. Remaining Useful Life (RUL) prediction is a key component of this process; however, many existing models struggle…

Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have shown that many of the…

Speech transcription, emotion recognition, and language identification are usually considered to be three different tasks. Each one requires a different model with a different architecture and training process. We propose using a recurrent…

Increasing the capacity of recurrent neural networks (RNN) usually involves augmenting the size of the hidden layer, with significant increase of computational cost. Recurrent neural tensor networks (RNTN) increase capacity using distinct…

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…

Considering deep sequence learning for practical application, two representative RNNs - LSTM and GRU may come to mind first. Nevertheless, is there no chance for other RNNs? Will there be a better RNN in the future? In this work, we propose…

Sparse tensor networks are commonly used to represent contractions over sparse tensors. Tensor contractions are higher-order analogs of matrix multiplication. Tensor networks arise commonly in many domains of scientific computing and data…

In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…

Biophysical modelling of the diffusion MRI signal provides estimates of specific microstructural tissue properties. Although nonlinear optimization such as non-linear least squares (NLLS) is the most widespread method for model estimation,…

Network quantization is arguably one of the most practical network compression approaches for reducing the enormous resource consumption of modern deep neural networks. They usually require diverse and subtle design choices for specific…