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 machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful fANOVA framework. In total, we summarize the results of 5400 experimental runs ($\approx 15$ years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Microsoft Multimedia（微软多媒体）
Time series prediction with deep learning methods, especially long short-term memory neural networks (LSTMs), have scored significant achievements in recent years. Despite the fact that the LSTMs can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within multiple time-steps is insufficient. To address this issue, an evolutionary attention-based LSTM training with competitive random search is proposed for multivariate time series prediction. By transferring shared parameters, an evolutionary attention learning approach is introduced…
Enhancing Speech Emotion Recognition Through Differentiable Architecture Search
University of Southern Queensland（南昆士兰大学）；Queensland University of Technology（昆士兰科技大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Imperial College London（伦敦帝国理工学院）
emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition
University of Southern Queensland（南昆士兰大学）；Queensland University of Technology（昆士兰科技大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Technical University of Munich（慕尼黑工业大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Imperial College London（帝国理工学院）
Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in ter…
The Transformer architecture is superior to RNN-based models in computational efficiency. Recently, GPT and BERT demonstrate the efficacy of Transformer models on various NLP tasks using pre-trained language models on large-scale corpora. Surprisingly, these Transformer architectures are suboptimal for language model itself. Neither self-attention nor the positional encoding in the Transformer is able to efficiently incorporate the word-level sequential context crucial to language modeling. In this paper, we explore effective Transformer architectures for language model, including adding addit…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Georgia Institute of Technology（佐治亚理工学院）；Purdue University（普渡大学）；University at Buffalo（布法罗大学）
Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive experiments have shown that, prominent neural architectures, such as ResNet in computer vision and LSTM in natural language processing, are generally good at extracting patterns from the input data and perform well on different downstream tasks. In this paper, we attempt to answer two fundamental questions related to NAS. (1) Is it necessary to use the performance of specific downstream tasks to evaluate and search f…
Google DeepMind（谷歌DeepMind）；Google（谷歌）；University of Warsaw（华沙大学）
In this paper, we propose and investigate a novel memory architecture for neural networks called Hierarchical Attentive Memory (HAM). It is based on a binary tree with leaves corresponding to memory cells. This allows HAM to perform memory access in O(log n) complexity, which is a significant improvement over the standard attention mechanism that requires O(n) operations, where n is the size of the memory. We show that an LSTM network augmented with HAM can learn algorithms for problems like merging, sorting or binary searching from pure input-output examples. In particular, it learns to sort …
University of British Columbia（不列颠哥伦比亚大学）；Microsoft Research（微软研究院）
This paper develops a model that addresses sentence embedding, a hot topic in current natural language processing research, using recurrent neural networks with Long Short-Term Memory (LSTM) cells. Due to its ability to capture long term memory, the LSTM-RNN accumulates increasingly richer information as it goes through the sentence, and when it reaches the last word, the hidden layer of the network provides a semantic representation of the whole sentence. In this paper, the LSTM-RNN is trained in a weakly supervised manner on user click-through data logged by a commercial web search engine. V…
Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via low-rank factorizations and parameter sharing schemes. Our goal is to investigate redundancies in recurrent architectures where compression can be admitted without losing performance. A hybrid strategy of using structured matrices in the bottom …
Gated recurrent networks such as those composed of Long Short-Term Memory (LSTM) nodes have recently been used to improve state of the art in many sequential processing tasks such as speech recognition and machine translation. However, the basic structure of the LSTM node is essentially the same as when it was first conceived 25 years ago. Recently, evolutionary and reinforcement learning mechanisms have been employed to create new variations of this structure. This paper proposes a new method, evolution of a tree-based encoding of the gated memory nodes, and shows that it makes it possible to…
IBM T.J. Watson Research Center（IBM TJ沃森研究中心）；University of Washington（华盛顿大学）；CONICET（国家科学技术研究委员会）；Harvard University（哈佛大学）
Many real-world data sets, especially in biology, are produced by complex nonlinear dynamical systems. In this paper, we focus on brain calcium imaging (CaI) of different organisms (zebrafish and rat), aiming to build a model of joint activation dynamics in large neuronal populations, including the whole brain of zebrafish. We propose a new approach for capturing dynamics of temporal SVD components that uses the coupled (multivariate) van der Pol (VDP) oscillator, a nonlinear ordinary differential equation (ODE) model describing neural activity, with a new parameter estimation technique that c…
The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits of the non-streaming model in streaming applications like voice search, it is commonly used in second pass re-scoring mode. The candidate hypothesis generated using steaming models is re-scored using a non-streaming model. In this work, we evaluate the non-streaming attention-based end-to-end ASR models on the Flipkart voice search task in both standalone an…
Character-level convolutional neural networks (char-CNN) require no knowledge of the semantic or syntactic structure of the language they classify. This property simplifies its implementation but reduces its classification accuracy. Increasing the depth of char-CNN architectures does not result in breakthrough accuracy improvements. Research has not established which char-CNN architectures are optimal for text classification tasks. Manually designing and training char-CNNs is an iterative and time-consuming process that requires expert domain knowledge. Evolutionary deep learning (EDL) techniq…
Time series forecasting (TSF) is one of the most important tasks in data science given the fact that accurate time series (TS) predictive models play a major role across a wide variety of domains including finance, transportation, health care, and power systems. Real-world utilization of machine learning (ML) typically involves (pre-)training models on collected, historical data and then applying them to unseen data points. However, in real-world applications, time series data streams are usually non-stationary and trained ML models usually, over time, face the problem of data or concept drift…
Deep learning builds deep architectures such as multi-layered artificial neural networks to effectively represent multiple features of input patterns. The adaptive structural learning method of Deep Belief Network (DBN) can realize a high classification capability while searching the optimal network structure during the training. The method can find the optimal number of hidden neurons of a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm to train the given input data, and then it can make a new layer in DBN by the layer generation algorithm to actualize a deep da…
