Related papers: EchoLSTM: A Self-Reflective Recurrent Network for …
We introduce multiplicative LSTM (mLSTM), a recurrent neural network architecture for sequence modelling that combines the long short-term memory (LSTM) and multiplicative recurrent neural network architectures. mLSTM is characterised by…
Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of…
Time series prediction can be generalized as a process that extracts useful information from historical records and then determines future values. Learning long-range dependencies that are embedded in time series is often an obstacle for…
Large language models (LLMs) suffer from proactive interference (PI): outdated information in the context window disrupts retrieval of current values. This interference degrades retrieval accuracy log-linearly as stale associations…
Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…
The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the…
Long Short-Term Memory (LSTM) is a special class of recurrent neural network, which has shown remarkable successes in processing sequential data. The typical architecture of an LSTM involves a set of states and gates: the states retain…
LSTM models used in current Machine Learning literature and applications, has a promising solution for permitting long term information using gating mechanisms that forget and reduce effect of current input information. However, even with…
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…
In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…
In this paper, we present Gamma-LSTM, an enhanced long short term memory (LSTM) unit, to enable learning of hierarchical representations through multiple stages of temporal abstractions. Gamma memory, a hierarchical memory unit, forms the…
The Long Short-Term Memory (LSTM) recurrent neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long input sequences. It has the potential to…
In this short note, we present an extension of long short-term memory (LSTM) neural networks to using a depth gate to connect memory cells of adjacent layers. Doing so introduces a linear dependence between lower and upper layer recurrent…
Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open challenge. Current…
Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel…
The ability to learn continuously in artificial neural networks (ANNs) is often limited by catastrophic forgetting, a phenomenon in which new knowledge becomes dominant. By taking mechanisms of memory encoding in neuroscience (aka. engrams)…
At the heart of time-series forecasting (TSF) lies a fundamental challenge: how can models efficiently and effectively capture long-range temporal dependencies across ever-growing sequences? While deep learning has brought notable progress,…
Recursive neural networks (RNN) and their recently proposed extension recursive long short term memory networks (RLSTM) are models that compute representations for sentences, by recursively combining word embeddings according to an…
Recently, recurrent neural networks have become state-of-the-art in acoustic modeling for automatic speech recognition. The long short-term memory (LSTM) units are the most popular ones. However, alternative units like gated recurrent unit…
Recent advancements in autoregressive networks with linear complexity have driven significant research progress, demonstrating exceptional performance in large language models. A representative model is the Extended Long Short-Term Memory…