Related papers: Yet Unnoticed in LSTM: Binary Tree Based Input Reo…
The emergence of Long Short-Term Memory (LSTM) solves the problems of vanishing gradient and exploding gradient in traditional Recurrent Neural Networks (RNN). LSTM, as a new type of RNN, has been widely used in various fields, such as text…
Transformers with linear recurrent modeling offer linear-time training and constant-memory inference. Despite their demonstrated efficiency and performance, pretraining such non-standard architectures from scratch remains costly and risky.…
Recurrent neural networks can be difficult to train on long sequence data due to the well-known vanishing gradient problem. Some architectures incorporate methods to reduce RNN state updates, therefore allowing the network to preserve…
Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computational costs and memory requirements. Ternarization, an extreme form of quantization, offers…
In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and contributed to numerous deep learning success stories, in…
Artificial neural networks are powerful models, which have been widely applied into many aspects of machine translation, such as language modeling and translation modeling. Though notable improvements have been made in these areas, the…
Tree-structured LSTM is promising way to consider long-distance interaction over hierarchies. However, there have been few research efforts on the hyperparameter tuning of the construction and traversal of tree-structured LSTM. To name a…
Recurrent neural architectures such as LSTM and GRU remain widely used in sequence modeling, but they continue to face two core limitations: redundant gate-specific parameters and reduced ability to retain information across long temporal…
Many state-of-art neural models designed for monotonicity reasoning perform poorly on downward inference. To address this shortcoming, we developed an attentive tree-structured neural network. It consists of a tree-based…
Previous RNN architectures have largely been superseded by LSTM, or "Long Short-Term Memory". Since its introduction, there have been many variations on this simple design. However, it is still widely used and we are not aware of a…
Learning-to-Rank (LTR) is a supervised machine learning approach that constructs models specifically designed to order a set of items or documents based on their relevance or importance to a given query or context. Despite significant…
Machine and deep learning-based algorithms are the emerging approaches in addressing prediction problems in time series. These techniques have been shown to produce more accurate results than conventional regression-based modeling. It has…
We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the…
Gating is a key technique used for integrating information from multiple sources by long short-term memory (LSTM) models and has recently also been applied to other models such as the highway network. Although gating is powerful, it is…
Recently, recurrent neural networks (RNNs) as powerful sequence models have re-emerged as a potential acoustic model for statistical parametric speech synthesis (SPSS). The long short-term memory (LSTM) architecture is particularly…
Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This…
As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…
This paper presents a novel unifying framework of bilinear LSTMs that can represent and utilize the nonlinear interaction of the input features present in sequence datasets for achieving superior performance over a linear LSTM and yet not…
Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…
Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the…