Using raw sensor data to model and train networks for Human Activity Recognition can be used in many different applications, from fitness tracking to safety monitoring applications. These models can be easily extended to be trained with different data sources for increased accuracies or an extension of classifications for different prediction classes. This paper goes into the discussion on the available dataset provided by WISDM and the unique features of each class for the different axes. Furthermore, the design of a Long Short Term Memory (LSTM) architecture model is outlined for the application of human activity recognition. An accuracy of above 94% and a loss of less than 30% has been reached in the first 500 epochs of training.
University of Electronic Science and Technology of China（电子科技大学）；Weill Cornell Medical College, Cornell University（康奈尔大学威尔康奈尔医学院）；Tencent Inc.（腾讯公司）
Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling. The hidden layers in RNNs can be regarded as the memory units, which are helpful in storing information in sequential contexts. However, when dealing with high dimensional input data, such as video and text, the input-to-hidden linear transformation in RNNs brings high memory usage and huge computational cost. This makes the training of RNNs unscalable and difficult. To address this challen…
ETH Zürich（苏黎世联邦理工学院）；University of Bologna（博洛尼亚大学）；Huawei Technologies（华为技术有限公司）
Recurrent neural networks such as Long Short-Term Memories (LSTMs) learn temporal dependencies by keeping an internal state, making them ideal for time-series problems such as speech recognition. However, the output-to-input feedback creates distinctive memory bandwidth and scalability challenges in designing accelerators for RNNs. We present Muntaniala, an RNN accelerator architecture for LSTM inference with a silicon-measured energy-efficiency of 3.25$TOP/s/W$ and performance of 30.53$GOP/s$ in UMC 65 $nm$ technology. The scalable design of Muntaniala allows running large RNN models by combi…
This study provides benchmarks for different implementations of LSTM units between the deep learning frameworks PyTorch, TensorFlow, Lasagne and Keras. The comparison includes cuDNN LSTMs, fused LSTM variants and less optimized, but more flexible LSTM implementations. The benchmarks reflect two typical scenarios for automatic speech recognition, notably continuous speech recognition and isolated digit recognition. These scenarios cover input sequences of fixed and variable length as well as the loss functions CTC and cross entropy. Additionally, a comparison between four different PyTorch vers…
Bidirectional Long Short-Term Memory (LSTM) is a special kind of Recurrent Neural Network (RNN) architecture which is designed to model sequences and their long-range dependencies more precisely than RNNs. This paper proposes to use deep bidirectional LSTM for sequence modeling as an approach to perform locality-sensitive hashing (LSH)-based sequence alignment. In particular, we use the deep bidirectional LSTM to learn features of LSH. The obtained LSH is then can be utilized to perform sequence alignment. We demonstrate the feasibility of the modeling sequences using the proposed LSTM-based m…
The University of Hong Kong（香港大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
The LSTM network was proposed to overcome the difficulty in learning long-term dependence, and has made significant advancements in applications. With its success and drawbacks in mind, this paper raises the question - do RNN and LSTM have long memory? We answer it partially by proving that RNN and LSTM do not have long memory from a statistical perspective. A new definition for long memory networks is further introduced, and it requires the model weights to decay at a polynomial rate. To verify our theory, we convert RNN and LSTM into long memory networks by making a minimal modification, and…
Short-term traffic forecasting based on deep learning methods, especially recurrent neural networks (RNN), has received much attention in recent years. However, the potential of RNN-based models in traffic forecasting has not yet been fully exploited in terms of the predictive power of spatial-temporal data and the capability of handling missing data. In this paper, we focus on RNN-based models and attempt to reformulate the way to incorporate RNN and its variants into traffic prediction models. A stacked bidirectional and unidirectional LSTM network architecture (SBU-LSTM) is proposed to assi…
Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, Long-Short-Term-Memory Networks (LSTMs) are commonly preferred in practice, as these networks are capable of learning long-term dependencies while avoiding the vanishing gradient problem. However, due to their large number of parameters, training LSTMs requires considerably longer training time compared to simple RNNs (SRNNs). In this paper, we achieve the online regression performance of LSTMs with SRNNs efficiently. To this end, we introd…
Efficient and accurate remaining useful life prediction is a key factor for reliable and safe usage of lithium-ion batteries. This work trains a long short-term memory recurrent neural network model to learn from sequential data of discharge capacities at various cycles and voltages and to work as a cycle life predictor for battery cells cycled under different conditions. Using experimental data of first 60 - 80 cycles, our model achieves promising prediction accuracy on test sets of around 80 samples.
In this paper, the performance of three deep learning methods for predicting short-term evolution and for reproducing the long-term statistics of a multi-scale spatio-temporal Lorenz 96 system is examined. The methods are: echo state network (a type of reservoir computing, RC-ESN), deep feed-forward artificial neural network (ANN), and recurrent neural network with long short-term memory (RNN-LSTM). This Lorenz 96 system has three tiers of nonlinearly interacting variables representing slow/large-scale ($X$), intermediate ($Y$), and fast/small-scale ($Z$) processes. For training or testing, on…
Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling. However, when processing high-dimensional data, RNNs typically require very large model sizes, thereby bringing a series of deployment challenges. Although the state-of-the-art tensor decomposition approaches can provide good model compression performance, these existing methods are still suffering some inherent limitations, such as restricted representation capability and insufficient model complexity reduction. To overcome these limitations, in this paper we propose to develop compact RNN models using H…
Long short-term memory (LSTM) is normally used in recurrent neural network (RNN) as basic recurrent unit. However,conventional LSTM assumes that the state at current time step depends on previous time step. This assumption constraints the time dependency modeling capability. In this study, we propose a new variation of LSTM, advanced LSTM (A-LSTM), for better temporal context modeling. We employ A-LSTM in weighted pooling RNN for emotion recognition. The A-LSTM outperforms the conventional LSTM by 5.5% relatively. The A-LSTM based weighted pooling RNN can also complement the state-of-the-art e…
While Recurrent Neural Networks (RNNs) are famously known to be Turing complete, this relies on infinite precision in the states and unbounded computation time. We consider the case of RNNs with finite precision whose computation time is linear in the input length. Under these limitations, we show that different RNN variants have different computational power. In particular, we show that the LSTM and the Elman-RNN with ReLU activation are strictly stronger than the RNN with a squashing activation and the GRU. This is achieved because LSTMs and ReLU-RNNs can easily implement counting behavior. …
Recurrent neural networks (RNNs) have shown outstanding performance on processing sequence data. However, they suffer from long training time, which demands parallel implementations of the training procedure. Parallelization of the training algorithms for RNNs are very challenging because internal recurrent paths form dependencies between two different time frames. In this paper, we first propose a generalized graph-based RNN structure that covers the most popular long short-term memory (LSTM) network. Then, we present a parallelization approach that automatically explores parallelisms of arbi…
The task of predicting future stock values has always been one that is heavily desired albeit very difficult. This difficulty arises from stocks with non-stationary behavior, and without any explicit form. Hence, predictions are best made through analysis of financial stock data. To handle big data sets, current convention involves the use of the Moving Average. However, by utilizing the Wavelet Transform in place of the Moving Average to denoise stock signals, financial data can be smoothened and more accurately broken down. This newly transformed, denoised, and more stable stock data can be …
Recurrent Neural Networks (RNNs) have long been recognized for their potential to model complex time series. However, it remains to be determined what optimization techniques and recurrent architectures can be used to best realize this potential. The experiments presented take a deep look into Hessian free optimization, a powerful second order optimization method that has shown promising results, but still does not enjoy widespread use. This algorithm was used to train to a number of RNN architectures including standard RNNs, long short-term memory, multiplicative RNNs, and stacked RNNs on the…
IST Austria（奥地利科学技术研究所）；TU Wien（维也纳工业大学）；MIT（麻省理工学院）
Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for modeling irregularly-sampled time series. These models, however, face difficulties when the input data possess long-term dependencies. We prove that similar to standard RNNs, the underlying reason for this issue is the vanishing or exploding of the gradient during training. This phenomenon is expressed by the ordinary differential equation (ODE) representation of the hidden state, regardless of the ODE solver's choice. We provide a solution by designing a new algorithm based on the long short-term memory …
University of Toronto（多伦多大学）；Carnegie Mellon University（卡内基梅隆大学）
The Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNNs) are a popular class of machine learning models for analyzing sequential data. Their training on modern GPUs, however, is limited by the GPU memory capacity. Our profiling results of the LSTM RNN-based Neural Machine Translation (NMT) model reveal that feature maps of the attention and RNN layers form the memory bottleneck and runtime is unevenly distributed across different layers when training on GPUs. Based on these two observations, we propose to recompute the feature maps rather than stashing them persistently in the GPU memo…
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully used for sequence labeling and sequence prediction tasks, such as handwriting recognition, language modeling, phonetic labeling of acoustic frames. However, in contrast to the deep neural networks, the use of RNNs in speech recognition has been limited to phone recognition in smal…
In machine learning, it is very important for a robot to be able to estimate dynamics from sequences of input data. This problem can be solved using a recurrent neural network. In this paper, we will discuss the preprocessing of 10 states of the dataset, then the use of a LSTM recurrent neural network to estimate one output state (dynamics) from the other 9 input states. We will discuss the architecture of the recurrent neural network, the data collection and preprocessing, the loss function, the results of the test data, and the discussion of changes that could improve the network. The result…
Electricity consumption has increased exponentially during the past few decades. This increase is heavily burdening the electricity distributors. Therefore, predicting the future demand for electricity consumption will provide an upper hand to the electricity distributor. Predicting electricity consumption requires many parameters. The paper presents two approaches with one using a Recurrent Neural Network (RNN) and another one using a Long Short Term Memory (LSTM) network, which only considers the previous electricity consumption to predict the future electricity consumption. These models wer…
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic models using such LSTM RNNs can be equaled by sequence trained phone models initialized with connectionist temporal classification (CTC). In this paper, we present techniques that further improve performance of LSTM RNN acoustic models for large vocabulary speech recognition. We s…
An essential task in predictive maintenance is the prediction of the Remaining Useful Life (RUL) through the analysis of multivariate time series. Using the sliding window method, Convolutional Neural Network (CNN) and conventional Recurrent Neural Network (RNN) approaches have produced impressive results on this matter, due to their ability to learn optimized features. However, sequence information is only partially modeled by CNN approaches. Due to the flatten mechanism in conventional RNNs, like Long Short Term Memories (LSTM), the temporal information within the window is not fully preserv…
Considering deep sequence learning for practical application, two representative RNNs - LSTM and GRU may come to mind first. Nevertheless, is there no chance for other RNNs? Will there be a better RNN in the future? In this work, we propose a novel, succinct and promising RNN - Fusion Recurrent Neural Network (Fusion RNN). Fusion RNN is composed of Fusion module and Transport module every time step. Fusion module realizes the multi-round fusion of the input and hidden state vector. Transport module which mainly refers to simple recurrent network calculate the hidden state and prepare to pass i…
We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up to 8 layers. We investigate the training aspect and study different variants of optimization methods, batching, truncated backpropagation, different regularization techniques such as dropout and $L_2$ regularization, and different gradient clipping variants. The major part of the experimental analysis was performed on the Quaero corpus. Additional experiments…
Scripts are an important part of any TV series. They narrate movements, actions and expressions of characters. In this paper, a case study is presented on how different sequence to sequence deep learning models perform in the task of generating new conversations between characters as well as new scenarios on the basis of a script (previous conversations). A comprehensive comparison between these models, namely, LSTM, GRU and Bidirectional RNN is presented. All the models are designed to learn the sequence of recurring characters from the input sequence. Each input sequence will contain, say "n…
Columbia University（哥伦比亚大学）；University of British Columbia（不列颠哥伦比亚大学）；Google Brain（谷歌大脑）；Microsoft Research（微软研究院）
Training recurrent neural networks (RNNs) on long sequence tasks is plagued with difficulties arising from the exponential explosion or vanishing of signals as they propagate forward or backward through the network. Many techniques have been proposed to ameliorate these issues, including various algorithmic and architectural modifications. Two of the most successful RNN architectures, the LSTM and the GRU, do exhibit modest improvements over vanilla RNN cells, but they still suffer from instabilities when trained on very long sequences. In this work, we develop a mean field theory of signal pr…
School of Computer & Information Sciences, University of Hyderabad（海得拉巴大学计算机与信息科学学院）
Language models, being at the heart of many NLP problems, are always of great interest to researchers. Neural language models come with the advantage of distributed representations and long range contexts. With its particular dynamics that allow the cycling of information within the network, `Recurrent neural network' (RNN) becomes an ideal paradigm for neural language modeling. Long Short-Term Memory (LSTM) architecture solves the inadequacies of the standard RNN in modeling long-range contexts. In spite of a plethora of RNN variants, possibility to add multiple memory cells in LSTM nodes was…
Department of Electrical and Computer Engineering Michigan State University（密歇根州立大学电气与计算机工程系）；Circuits, Systems, and Neural Networks (CSANN) Lab（电路、系统与神经网络（CSANN）实验室）
Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input vector sequence, (ii) one adaptive weight matrix multiplied by the previous memory/state vector, and (iii) one adaptive bias vector. In effect, they augment the simple Recurrent Neural Networks (sRNNs) structure with the addition of a "memory cell" and the incorporation of at most 3 gating signals. The standard LSTM structure and components encompass redundancy …
Institute of Neuroinformatics（神经信息学研究所）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）
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 memory over long temporal intervals. To address these problems of convergence, this paper proposes a timing-gated LSTM RNN model, called the Gaussian-gated LSTM (g-LSTM). The time gate controls when a neuron can be updated during training, enabling longer memory persistence and better error-gradient flow. This model captures long-temporal dependencies better than…
SMILE Lab, University of Electronic Science and Technology of China（电子科技大学SMILE实验室）；Dept. of Computer Science, Brown University（布朗大学计算机科学系）；School of Computing, University of Utah（犹他大学计算机学院）；Xjera Labs, Pte.Ltd（Xjera实验室私人有限公司）
Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs from solving many important computer vision tasks, such as Action Recognition in Videos and Image Captioning. To overcome this problem, we propose a compact and flexible structure, namely Block-Term tensor decomposition, which greatly reduces the parameters of RNNs and improves their training efficiency. Compared with alternative low-rank approximations, such…
Recurrent Neural Networks (RNNs) are used in applications that learn dependencies in data sequences, such as speech recognition, human activity recognition, and anomaly detection. In recent years, newer RNN variants, such as GRUs and LSTMs, have been used for implementing these applications. As many of these applications are employed in real-time scenarios, accelerating RNN/LSTM/GRU inference is crucial. In this paper, we propose a novel photonic hardware accelerator called RecLight for accelerating simple RNNs, GRUs, and LSTMs. Simulation results indicate that RecLight achieves 37x lower ener…
Universitas Indonesia（印度尼西亚大学）；Nara Institute of Science and Technology（奈良先端科学技术大学）
Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capture more information from inputs. For modeling long-term dependencies in a dataset, the gating mechanism concept can help RNNs remember and forget previous information. Representing the hidden layers of an RNN with more expressive operations (i.e., tensor products) helps it learn a more complex relationship between the current input and the previous hidden layer information. Th…
University of Victoria（维多利亚大学）；Fortinet Canada Inc.（Fortinet加拿大公司）
This paper proposes recurrent neuron networks (RNNs) for a fingerprinting indoor localization using WiFi. Instead of locating user's position one at a time as in the cases of conventional algorithms, our RNN solution aims at trajectory positioning and takes into account the relation among the received signal strength indicator (RSSI) measurements in a trajectory. Furthermore, a weighted average filter is proposed for both input RSSI data and sequential output locations to enhance the accuracy among the temporal fluctuations of RSSI. The results using different types of RNN including vanilla RN…
Recurrent Neural Networks (RNNs) have been widely applied to sequential data analysis. Due to their complicated modeling structures, however, the theory behind is still largely missing. To connect theory and practice, we study the generalization properties of vanilla RNNs as well as their variants, including Minimal Gated Unit (MGU), Long Short Term Memory (LSTM), and Convolutional (Conv) RNNs. Specifically, our theory is established under the PAC-Learning framework. The generalization bound is presented in terms of the spectral norms of the weight matrices and the total number of parameters. …
Institute of Neuroinformatics（神经信息学研究所）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）
Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns from temporal sequences. However, current RNN models are ill-suited to process irregularly sampled data triggered by events generated in continuous time by sensors or other neurons. Such data can occur, for example, when the input comes from novel event-driven artificial sensors that generate sparse, asynchronous streams of events or from multiple conventional sensors with different update intervals. In this work, we introduce the Phased LSTM model, which extends the LSTM unit by adding a new time …
We have shown previously that our parameter-reduced variants of Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNN) are comparable in performance to the standard LSTM RNN on the MNIST dataset. In this study, we show that this is also the case for two diverse benchmark datasets, namely, the review sentiment IMDB and the 20 Newsgroup datasets. Specifically, we focus on two of the simplest variants, namely LSTM_6 (i.e., standard LSTM with three constant fixed gates) and LSTM_C6 (i.e., LSTM_6 with further reduced cell body input block). We demonstrate that these two aggressively reduced-…
University of Michigan（密歇根大学）；Institute for Healthcare Policy & Innovation（医疗政策与创新研究所）
Recurrent neural networks (RNNs) are commonly applied to clinical time-series data with the goal of learning patient risk stratification models. Their effectiveness is due, in part, to their use of parameter sharing over time (i.e., cells are repeated hence the name recurrent). We hypothesize, however, that this trait also contributes to the increased difficulty such models have with learning relationships that change over time. Conditional shift, i.e., changes in the relationship between the input X and the output y, arises when risk factors associated with the event of interest change over t…
Brown University（布朗大学）；Harvard Medical School（哈佛医学院）
Intracortical brain computer interfaces (iBCIs) using linear Kalman decoders have enabled individuals with paralysis to control a computer cursor for continuous point-and-click typing on a virtual keyboard, browsing the internet, and using familiar tablet apps. However, further advances are needed to deliver iBCI-enabled cursor control approaching able-bodied performance. Motivated by recent evidence that nonlinear recurrent neural networks (RNNs) can provide higher performance iBCI cursor control in nonhuman primates (NHPs), we evaluated decoding of intended cursor velocity from human motor c…
Université de Montréal（蒙特利尔大学）；Huawei Noah’s Ark Research Lab（华为诺亚方舟实验室）
Recurrent neural networks (RNN) such as long-short-term memory (LSTM) networks are essential in a multitude of daily live tasks such as speech, language, video, and multimodal learning. The shift from cloud to edge computation intensifies the need to contain the growth of RNN parameters. Current research on RNN shows that despite the performance obtained on convolutional neural networks (CNN), keeping a good performance in compressed RNNs is still a challenge. Most of the literature on compression focuses on CNNs using matrix product (MPO) operator tensor trains. However, matrix product state …
Toyota Technological Institute（丰田工业大学）；Toyota Technological Institute at Chicago（芝加哥丰田工业研究所）
We present a novel end-to-end neural model to extract entities and relations between them. Our recurrent neural network based model captures both word sequence and dependency tree substructure information by stacking bidirectional tree-structured LSTM-RNNs on bidirectional sequential LSTM-RNNs. This allows our model to jointly represent both entities and relations with shared parameters in a single model. We further encourage detection of entities during training and use of entity information in relation extraction via entity pretraining and scheduled sampling. Our model improves over the stat…
Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks. However, these models are computationally more expensive than N-gram LMs for decoding, and thus, challenging to integrate into speech recognizers. Recent research has proposed the use of lattice-rescoring algorithms using RNNLMs and LSTMLMs as an efficient strategy to integrate these models into a speech recognition system. In this paper, we evaluate existing lattice rescoring algorithms along with ne…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Adobe Systems, Inc.（奥多比系统公司）
In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test likelihood and faster convergence compared to regular full RNNs in most of our experiments. We show the benefits of using diagonal recurrent matrices with popularly used LSTM and GRU architectures as well as with the vanilla RNN architecture, on four standard symbolic music datasets.
Schmalkalden University of Applied Sciences（施马尔卡尔登应用科学大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) are one of the most powerful dynamic classifiers publicly known. The network itself and the related learning algorithms are reasonably well documented to get an idea how it works. This paper will shed more light into understanding how LSTM-RNNs evolved and why they work impressively well, focusing on the early, ground-breaking publications. We significantly improved documentation and fixed a number of errors and inconsistencies that accumulated in previous publications. To support understanding we as well revised and unified the notat…
Faculdade de Engenharia（工程学院）；Universidade do Porto（波尔图大学）；INESC TEC（葡萄牙系统与计算机工程研究所（技术与科学））；Fraunhofer AICOS（弗劳恩霍夫辅助信息与通信系统研究所）；LIACC（人工智能与计算机科学实验室）；Inovretail（Inovretail公司）
Forecasting accuracy is reliant on the quality of available past data. Data disruptions can adversely affect the quality of the generated model (e.g. unexpected events such as out-of-stock products when forecasting demand). We address this problem by pastcasting: predicting how data should have been in the past to explain the future better. We propose Pastprop-LSTM, a data-centric backpropagation algorithm that assigns part of the responsibility for errors to the training data and changes it accordingly. We test three variants of Pastprop-LSTM on forecasting competition datasets, M4 and M5, pl…
School of Electrical and Computer Engineering, University of Tehran（德黑兰大学电气与计算机工程学院）；Division of Intelligent Future Technologies, Malardalen University（马拉达伦大学智能未来技术系）
Recurrent Neural Networks (RNN) are widely used for learning sequences in applications such as EEG classification. Complex RNNs could be hardly deployed on wearable devices due to their computation and memory-intensive processing patterns. Generally, reduction in precision leads much more efficiency and binarized RNNs are introduced as energy-efficient solutions. However, naive binarization methods lead to significant accuracy loss in EEG classification. In this paper, we propose a multi-level binarized LSTM, which significantly reduces computations whereas ensuring an accuracy pretty close to…
This paper is based on a machine learning project at the Norwegian University of Science and Technology, fall 2020. The project was initiated with a literature review on the latest developments within time-series forecasting methods in the scientific community over the past five years. The paper summarizes the essential aspects of this research. Furthermore, in this paper, we introduce an LSTM cell's architecture, and explain how different components go together to alter the cell's memory and predict the output. Also, the paper provides the necessary formulas and foundations to calculate a for…
As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We focus on recurrent neural networks (RNNs), state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining an RNN with a hidden Markov model (HMM), a simpler and more transparent model. We explore various combinations of RNNs and HMMs: an HMM trained on LSTM states; a hybrid model where an HMM is tr…
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) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linearly dependent on the input length, and all inputs are read regardless of their importance. Efforts to speed up this inference, known as 'neural speed reading', either ignore or skim over part of the input. We present Structural-Jump-LSTM: the first neural speed reading model to both skip and jump text during inference. The model consists of a standard LSTM and two agents: one ca…
Recurrent neural network(RNN) has been broadly applied to natural language processing(NLP) problems. This kind of neural network is designed for modeling sequential data and has been testified to be quite efficient in sequential tagging tasks. In this paper, we propose to use bi-directional RNN with long short-term memory(LSTM) units for Chinese word segmentation, which is a crucial preprocess task for modeling Chinese sentences and articles. Classical methods focus on designing and combining hand-craft features from context, whereas bi-directional LSTM network(BLSTM) does not need any prior k…
LIA - University of Avignon（LIA - 阿维尼翁大学）；EDD；McGill University（麦吉尔大学）
Recently, machine learning methods have provided a broad spectrum of original and efficient algorithms based on Deep Neural Networks (DNN) to automatically predict an outcome with respect to a sequence of inputs. Recurrent hidden cells allow these DNN-based models to manage long-term dependencies such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM). Nevertheless, these RNNs process a single input stream in one (LSTM) or two (Bidirectional LSTM) directions. But most of the information available nowadays is from multistreams or multimedia documents, and require RNNs to proce…
University of Washington（华盛顿大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Google（谷歌）；Microsoft Research（微软研究院）；Amazon（亚马逊）；Mitsubishi Electric（三菱电机）；MERL（三菱电机研究实验室）
In this paper, we extend the deep long short-term memory (DLSTM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers. These direct links, called highway connections, enable unimpeded information flow across different layers and thus alleviate the gradient vanishing problem when building deeper LSTMs. We further introduce the latency-controlled bidirectional LSTMs (BLSTMs) which can exploit the whole history while keeping the latency under control. Efficient algorithms are proposed to train these novel networks using both frame and sequence …
Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a novel approach of using attention mechanism to build an end-to-end architecture for height and age estimation. The attention mechanism is combined with Long Short-Term Memory(LSTM) encoder which is able to capture long-term dependencies in the input acoustic features. We modify the conventionally used Attention -- which calculates context vectors the sum of attention only across timeframes -- by introducing a modified c…
