Related papers: Dual Memory Neural Computer for Asynchronous Two-v…

We present a novel LSTM cell architecture capable of learning both intra- and inter-perspective relationships available in visual sequences captured from multiple perspectives. Our architecture adopts a novel recurrent joint learning…

Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained from psychological studies, we designed a new model called…

In this paper, we consider the problem of multi-view clustering on incomplete views. Compared with complete multi-view clustering, the view-missing problem increases the difficulty of learning common representations from different views. To…

This paper introduces an innovative multi-modal fusion deep learning approach to overcome the drawbacks of traditional single-modal recognition techniques. These drawbacks include incomplete information and limited diagnostic accuracy.…

Intelligence necessitates memory. Without memory, humans fail to perform various nontrivial tasks such as reading novels, playing games or solving maths. As the ultimate goal of machine learning is to derive intelligent systems that learn…

Understanding and mapping a new environment are core abilities of any autonomously navigating agent. While classical robotics usually estimates maps in a stand-alone manner with SLAM variants, which maintain a topological or metric…

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

We propose a video story question-answering (QA) architecture, Multimodal Dual Attention Memory (MDAM). The key idea is to use a dual attention mechanism with late fusion. MDAM uses self-attention to learn the latent concepts in scene…

Software developed helps world a better place ranging from system software, open source, application software and so on. Software engineering does have neural network models applied to code suggestion, bug report summarizing and so on to…

Multiple views of data, both naturally acquired (e.g., image and audio) and artificially produced (e.g., via adding different noise to data samples), have proven useful in enhancing representation learning. Natural views are often handled…

In recent years, model-free methods that use deep learning have achieved great success in many different reinforcement learning environments. Most successful approaches focus on solving a single task, while multi-task reinforcement learning…

This paper presents a novel fusion method for integrating an external language model (LM) into the Transformer based sequence-to-sequence (seq2seq) model. While paired data are basically required to train the seq2seq model, the external LM…

Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced…

The human visual system uses two parallel pathways for spatial processing and object recognition. In contrast, computer vision systems tend to use a single feedforward pathway, rendering them less robust, adaptive, or efficient than human…

We consider a sequence of related multivariate time series learning tasks, such as predicting failures for different instances of a machine from time series of multi-sensor data, or activity recognition tasks over different individuals from…

A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data. The outstanding results of Transformers-based networks (e.g., Large…

Introducing variability while maintaining coherence is a core task in learning to generate utterances in conversation. Standard neural encoder-decoder models and their extensions using conditional variational autoencoder often result in…

Encoder-decoder recurrent neural network models (RNN Seq2Seq) have achieved great success in ubiquitous areas of computation and applications. It was shown to be successful in modeling data with both temporal and spatial dependencies for…

Multi-modal Record Linkage is the process of matching multi-modal records from multiple sources that represent the same entity. This field has not been explored in research and we propose two solutions based on Deep Learning architectures…

Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…