Quaternion Recurrent Neural Networks
Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characterized by strong internal dependencies between the dimensions of the input vector. We propose a novel quaternion recurrent neural network (QRNN), alongside with a quaternion long-short term memory neural network (QLSTM), that take into account both the external relations and these internal structural dependencies with the quaternion algebra. Similarly to capsules, quaternions allow the QRNN to code internal dependencies by composing and processing multidimensional features as single entities, while the recurrent operation reveals correlations between the elements composing the sequence. We show that both QRNN and QLSTM achieve better performances than RNN and LSTM in a realistic application of automatic speech recognition. Finally, we show that QRNN and QLSTM reduce by a maximum factor of 3.3x the number of free parameters needed, compared to real-valued RNNs and LSTMs to reach better results, leading to a more compact representation of the relevant information.
Code (3)
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Quaternion-Valued Recurrent Projection Neural Networks on Unit Quaternions
Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks …
An Introduction to Quaternion-Valued Recurrent Projection Neural Networks
Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we introduce the quaternion-valued recurrent projection neural network…
Predicting Rigid Body Dynamics using Dual Quaternion Recurrent Neural Networks with Quaternion Attention
We propose a novel neural network architecture based on dual quaternions which allow for a compact representation of informations with a main focus on describing rigid body movements. To cover the dynamic behavior inhere…
PositionQuaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learning (RTRL) algorithm and the maximum cor…
motion predictionBidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition