Ionic models, the set of ordinary differential equations (ODEs) describing the time evolution of the state of excitable cells, are the cornerstone of modeling in neuro- and cardiac electrophysiology. Modern ionic models can have tens of state variables and hundreds of tunable parameters. Fitting ionic models to experimental data, which usually covers only a limited subset of state variables, remains a challenging problem. In this paper, we describe a recurrent neural network architecture designed specifically to encode ionic models. The core of the model is a Gating Neural Network (GNN) layer, capturing the dynamics of classic (Hodgkin-Huxley) gating variables. The network is trained in two steps: first, it learns the theoretical model coded in a set of ODEs, and second, it is retrained on experimental data. The retrained network is interpretable, such that its results can be incorporated back into the model ODEs. We tested the GNN networks using simulated ventricular action potential signals and showed that it could deduce physiologically-feasible alterations of ionic currents. Such domain-specific neural networks can be employed in the exploratory phase of data assimilation before further fine-tuning using standard optimization techniques.
Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）
University of Liège（列日大学）；Institut Polytechnique de Paris（巴黎理工学院）
Reinforcement learning aims to learn optimal policies from interaction with environments whose dynamics are unknown. Many methods rely on the approximation of a value function to derive near-optimal policies. In partially observable environments, these functions depend on the complete sequence of observations and past actions, called the history. In this work, we show empirically that recurrent neural networks trained to approximate such value functions internally filter the posterior probability distribution of the current state given the history, called the belief. More precisely, we show th…
Using historical data to predict future events has many applications in the real world, such as stock price prediction; the robot localization. In the past decades, the Convolutional long short-term memory (LSTM) networks have achieved extraordinary success with sequential data in the related field. However, traditional recurrent neural networks (RNNs) keep the hidden states in a deterministic way. In this paper, we use the particles to approximate the distribution of the latent state and show how it can extend into a more complex form, i.e., the Encoder-Decoder mechanism. With the proposed co…
We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks. Whereas previous works only apply batch normalization to the input-to-hidden transformation of RNNs, we demonstrate that it is both possible and beneficial to batch-normalize the hidden-to-hidden transition, thereby reducing internal covariate shift between time steps. We evaluate our proposal on various sequential problems such as sequence classification, language modeling and question answering. Our empirical results show that our batch-normalized LSTM consistently leads to f…
University of Tennessee（田纳西大学）；The University of Manchester（曼彻斯特大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
Hidden Markov models (HMMs) are commonly used for disease progression modeling when the true patient health state is not fully known. Since HMMs typically have multiple local optima, incorporating additional patient covariates can improve parameter estimation and predictive performance. To allow for this, we develop hidden Markov recurrent neural networks (HMRNNs), a special case of recurrent neural networks that combine neural networks' flexibility with HMMs' interpretability. The HMRNN can be reduced to a standard HMM, with an identical likelihood function and parameter interpretations, but …
There is an implicit assumption that by unfolding recurrent neural networks (RNN) in finite time, the misspecification of choosing a zero value for the initial hidden state is mitigated by later time steps. This assumption has been shown to work in practice and alternative initialization may be suggested but often overlooked. In this paper, we propose a method of parameterizing the initial hidden state of an RNN. The resulting architecture, referred to as a Contextual RNN, can be trained end-to-end. The performance on an associative retrieval task is found to improve by conditioning the RNN in…
Tel Aviv University（特拉维夫大学）；Facebook AI Research（Facebook人工智能研究院）
We propose a novel recurrent neural network model, where the hidden state $h_t$ is obtained by permuting the vector elements of the previous hidden state $h_{t-1}$ and adding the output of a learned function $b(x_t)$ of the input $x_t$ at time $t$. In our model, the prediction is given by a second learned function, which is applied to the hidden state $s(h_t)$. The method is easy to implement, extremely efficient, and does not suffer from vanishing nor exploding gradients. In an extensive set of experiments, the method shows competitive results, in comparison to the leading literature baseline…
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…
Learning Sequence Attractors in Recurrent Networks with Hidden Neurons
Peking University（北京大学）；School of Psychological and Cognitive Sciences（心理与认知科学学院）；IDG/McGovern Institute for Brain Research（IDG/麦戈文脑研究所）；Academy for Advanced Interdisciplinary Studies（前沿交叉学科研究院）
Viewing recurrent neural networks (RNNs) as continuous-time dynamical systems, we propose a recurrent unit that describes the hidden state's evolution with two parts: a well-understood linear component plus a Lipschitz nonlinearity. This particular functional form facilitates stability analysis of the long-term behavior of the recurrent unit using tools from nonlinear systems theory. In turn, this enables architectural design decisions before experimentation. Sufficient conditions for global stability of the recurrent unit are obtained, motivating a novel scheme for constructing hidden-to-hidd…
Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios
KIT（卡尔斯鲁厄理工学院）；University Of Lincoln（林肯大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Indian Institute Of Technology, Kanpur（印度理工学院坎普尔分校）
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the hidden-to-hidden transition can be reversed---offer a path to reduce the memory requirements of training, as hidden states need not be stored and instead can be recomputed during backpropagation. We first show that perfectly reversible RNNs, which require no storage of the hidden activations, are fundamentally limited because they cannot forget information from the…
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, state of the art models in speech recognition and translation. Our approach to increasing interpretability is by combining a long short-term memory (LSTM) model with a hidden Markov model (HMM), a simpler and more transparent model. We add the HMM state probabilities to the output layer of the LSTM, and then train the HMM…
In this paper, we explore the inclusion of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining elements of the variational autoencoder. We argue that through the use of high-level latent random variables, the variational RNN (VRNN)1 can model the kind of variability observed in highly structured sequential data such as natural speech. We empirically evaluate the proposed model against related sequential models on four speech datasets and one handwriting dataset. Our results show the important roles that latent random variables can play in the …
Université de Montréal（蒙特利尔大学）；Aalto University School of Science（阿尔托大学理学院）
In this paper, we explore different ways to extend a recurrent neural network (RNN) to a \textit{deep} RNN. We start by arguing that the concept of depth in an RNN is not as clear as it is in feedforward neural networks. By carefully analyzing and understanding the architecture of an RNN, however, we find three points of an RNN which may be made deeper; (1) input-to-hidden function, (2) hidden-to-hidden transition and (3) hidden-to-output function. Based on this observation, we propose two novel architectures of a deep RNN which are orthogonal to an earlier attempt of stacking multiple recurre…
University of Pisa（比萨大学）；University of Padova（帕多瓦大学）
The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be introduced into a neural architecture by an appropriate modularization of the dynamic memory. In this paper we propose a novel incrementally trained recurrent architecture targeting explicitly multi-scale learning. First, we show how to extend the architecture of a simple RNN by separating its hidden state into different modules, each subsampling the network hidden…
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…
Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high correlation between hidden states. These challenges can be mitigated by integrating second-order terms in the hidden-state update. One such model, multiplicative Long Short-Term Memory (mLSTM) is particularly interesting in its original formulation because of the sharing of its second-order term, referred to as the intermediate state. We explore these archit…
Universidad de Buenos Aires（布宜诺斯艾利斯大学）；University of Cambridge（剑桥大学）；Université de Montréal（蒙特利尔大学）
Recurrent neural networks (RNNs) are notoriously difficult to train. When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and exploding gradients, especially when trying to learn long-term dependencies. To circumvent this problem, we propose a new architecture that learns a unitary weight matrix, with eigenvalues of absolute value exactly 1. The challenge we address is that of parametrizing unitary matrices in a way that does not require expensive computations (such as eigendecomposit…
To model time-varying nonlinear temporal dynamics in sequential data, a recurrent network capable of varying and adjusting the recurrence depth between input intervals is examined. The recurrence depth is extended by several intermediate hidden state units, and the weight parameters involved in determining these units are dynamically calculated. The motivation behind the paper lies on overcoming a deficiency in Recurrent Highway Networks and improving their performances which are currently at the forefront of RNNs: 1) Determining the appropriate number of recurrent depth in RHN for different t…
Université de Montréal（蒙特利尔大学）；University of Southern California（南加州大学）
Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent work has shown that normalizing intermediate representations of neural networks can significantly improve convergence rates in feedforward neural networks . In particular, batch normalization, which uses mini-batch statistics to standardize features, was shown to significantly reduce training time. In this paper, we show that applying batch normalization to the hidden-to-hidden…
As an important part of intelligent transportation systems, traffic forecasting has attracted tremendous attention from academia and industry. Despite a lot of methods being proposed for traffic forecasting, it is still difficult to model complex spatial-temporal dependency. Temporal dependency includes short-term dependency and long-term dependency, and the latter is often overlooked. Spatial dependency can be divided into two parts: distance-based spatial dependency and hidden spatial dependency. To model complex spatial-temporal dependency, we propose a novel framework for traffic forecasti…
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…
Learning how to estimate a connectional brain template(CBT) from a population of brain multigraphs, where each graph (e.g., functional) quantifies a particular relationship between pairs of brain regions of interest (ROIs), allows to pin down the unique connectivity patterns shared across individuals. Specifically, a CBT is viewed as an integral representation of a set of highly heterogeneous graphs and ideally meeting the centeredness (i.e., minimum distance to all graphs in the population) and discriminativeness (i.e., distinguishes the healthy from the disordered population) criteria. So fa…
Time series forecasting based on deep architectures has been gaining popularity in recent years due to their ability to model complex non-linear temporal dynamics. The recurrent neural network is one such model capable of handling variable-length input and output. In this paper, we leverage recent advances in deep generative models and the concept of state space models to propose a stochastic adaptation of the recurrent neural network for multistep-ahead time series forecasting, which is trained with stochastic gradient variational Bayes. In our model design, the transition function of the rec…
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Classification of posts in social media such as Twitter is difficult due to the noisy and short nature of texts. Sequence classification models based on recurrent neural networks (RNN) are popular for classifying posts that are sequential in nature. RNNs assume the hidden representation dynamics to evolve in a discrete manner and do not consider the exact time of the posting. In this work, we propose to use recurrent neural ordinary differential equations (RNODE) for social media post classification which consider the time of posting and allow the computation of hidden representation to evolve…
University of Pisa（比萨大学）；University of Padova（帕多瓦大学）
Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design and training of recurrent neural networks. We propose a new model, the Linear Memory Network, which features an encoding-based memorization component built with a linear autoencoder for sequences. We extend the memorization component with a modular memory that encodes the hidden state sequence at different sampling frequencies. Additionally, we provide a spe…
Recently recurrent neural networks (RNN) has been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN is a difficult task, partly because there are many competing and complex hidden units (such as LSTM and GRU). We propose a gated unit for RNN, named as Minimal Gated Unit (MGU), since it only contains one gate, which is a minimal design among all gated hidden units. The design of MGU benefits from evaluation results on LSTM and GRU in the literature. Experiments on various sequence data show that MGU has comparable accuracy with GRU, but…
Humboldt-Universität zu Berlin（柏林洪堡大学）；Bosch Center for AI（博世人工智能中心）
Recurrent neural networks (RNNs) are a popular choice for modeling sequential data. Modern RNN architectures assume constant time-intervals between observations. However, in many datasets (e.g. medical records) observation times are irregular and can carry important information. To address this challenge, we propose continuous recurrent units (CRUs) -- a neural architecture that can naturally handle irregular intervals between observations. The CRU assumes a hidden state, which evolves according to a linear stochastic differential equation and is integrated into an encoder-decoder framework. T…
In recent years significant progress has been made in successfully training recurrent neural networks (RNNs) on sequence learning problems involving long range temporal dependencies. The progress has been made on three fronts: (a) Algorithmic improvements involving sophisticated optimization techniques, (b) network design involving complex hidden layer nodes and specialized recurrent layer connections and (c) weight initialization methods. In this paper, we focus on recently proposed weight initialization with identity matrix for the recurrent weights in a RNN. This initialization is specifica…
In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data. We propose to add residual connections across timesteps to RNN, which explicitly enhances the interaction between current state and hidden states that are several timesteps apart. This also allows training errors to be directly back-propagated through residual connections and effectively alleviates gradient vanishing problem. We further reformulate an attention mechanism over residual connections. An attention gate is defined to summarize the individua…
We observe that the standard log likelihood training objective for a Recurrent Neural Network (RNN) model of time series data is equivalent to a variational Bayesian training objective, given the proper choice of generative and inference models. This perspective may motivate extensions to both RNNs and variational Bayesian models. We propose one such extension, where multiple particles are used for the hidden state of an RNN, allowing a natural representation of uncertainty or multimodality.
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Recurrent neural networks (RNNs) have brought a lot of advancements in sequence labeling tasks and sequence data. However, their effectiveness is limited when the observations in the sequence are irregularly sampled, where the observations arrive at irregular time intervals. To address this, continuous time variants of the RNNs were introduced based on neural ordinary differential equations (NODE). They learn a better representation of the data using the continuous transformation of hidden states over time, taking into account the time interval between the observations. However, they are still…
Swiss Center for Electronics and Microtechnology (CSEM)（瑞士电子与微技术中心）
We developed a convolutional recurrent neural network to classify 12-lead ECG signals for the challenge of PhysioNet/ Computing in Cardiology 2020 as team Pink Irish Hat. The model combines convolutional and recurrent layers, takes sliding windows of ECG signals as input and yields the probability of each class as output. The convolutional part extracts features from each sliding window. The bi-directional gated recurrent unit (GRU) layer and an attention layer aggregate these features from all windows into a single feature vector. Finally, a dense layer outputs class probabilities. The final …
Zhengzhou University（郑州大学）；Hefei University of Technology（合肥工业大学）；Dalian Neusoft University of Information（大连东软信息学院）
In this paper, we present an effective deep prediction framework based on robust recurrent neural networks (RNNs) to predict the likely therapeutic classes of medications a patient is taking, given a sequence of diagnostic billing codes in their record. Accurately capturing the list of medications currently taken by a given patient is extremely challenging due to undefined errors and omissions. We present a general robust framework that explicitly models the possible contamination through overtime decay mechanism on the input billing codes and noise injection into the recurrent hidden states, …
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…
Informatics Institute（信息学研究所）；University of Amsterdam（阿姆斯特丹大学）
Earlier approaches indirectly studied the information captured by the hidden states of recurrent and non-recurrent neural machine translation models by feeding them into different classifiers. In this paper, we look at the encoder hidden states of both transformer and recurrent machine translation models from the nearest neighbors perspective. We investigate to what extent the nearest neighbors share information with the underlying word embeddings as well as related WordNet entries. Additionally, we study the underlying syntactic structure of the nearest neighbors to shed light on the role of …
University of Pittsburgh（匹兹堡大学）；Imperial College（帝国理工学院）
Biomedical signals carry signature rhythms of complex physiological processes that control our daily bodily activity. The properties of these rhythms indicate the nature of interaction dynamics among physiological processes that maintain a homeostasis. Abnormalities associated with diseases or disorders usually appear as disruptions in the structure of the rhythms which makes isolating these rhythms and the ability to differentiate between them, indispensable. Computer aided diagnosis systems are ubiquitous nowadays in almost every medical facility and more closely in wearable technology, and …
Recently, three dimensional (3D) convolutional neural networks (CNNs) have emerged as dominant methods to capture spatiotemporal representations in videos, by adding to pre-existing 2D CNNs a third, temporal dimension. Such 3D CNNs, however, are anti-causal (i.e., they exploit information from both the past and the future frames to produce feature representations, thus preventing their use in online settings), constrain the temporal reasoning horizon to the size of the temporal convolution kernel, and are not temporal resolution-preserving for video sequence-to-sequence modelling, as, for inst…
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）；Boston University（波士顿大学）
We propose a novel {\it Equilibrated Recurrent Neural Network} (ERNN) to combat the issues of inaccuracy and instability in conventional RNNs. Drawing upon the concept of autapse in neuroscience, we propose augmenting an RNN with a time-delayed self-feedback loop. Our sole purpose is to modify the dynamics of each internal RNN state and, at any time, enforce it to evolve close to the equilibrium point associated with the input signal at that time. We show that such self-feedback helps stabilize the hidden state transitions leading to fast convergence during training while efficiently learning …
McGill University（麦吉尔大学）；Pennsylvania State University（宾夕法尼亚州立大学）
We propose an approach that connects recurrent networks with different orders of hidden interaction with regular grammars of different levels of complexity. We argue that the correspondence between recurrent networks and formal computational models gives understanding to the analysis of the complicated behaviors of recurrent networks. We introduce an entropy value that categorizes all regular grammars into three classes with different levels of complexity, and show that several existing recurrent networks match grammars from either all or partial classes. As such, the differences between regul…
RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning
National University of Singapore（新加坡国立大学）；Guangming Laboratory（光明实验室）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of British Columbia（不列颠哥伦比亚大学）；Shanghai Jiao Tong University（上海交通大学）；Tencent（腾讯）
Seoul National University（首尔大学）；Seoul National University of Science and Technology（首尔科学技术大学）；NAVER Corp.（NAVER公司）
Recent advances in next-generation sequencing technologies have facilitated the use of deoxyribonucleic acid (DNA) as a novel covert channels in steganography. There are various methods that exist in other domains to detect hidden messages in conventional covert channels. However, they have not been applied to DNA steganography. The current most common detection approaches, namely frequency analysis-based methods, often overlook important signals when directly applied to DNA steganography because those methods depend on the distribution of the number of sequence characters. To address this lim…
Faculty of Computer Science and Engineering The Hebrew University of Jerusalem（计算机科学与工程学院 希伯来大学耶路撒冷分校）；The Hebrew University of Jerusalem（希伯来大学耶路撒冷分校）；Faculty of Computer Science and Engineering（计算机科学与工程学院）
A key attribute that drives the unprecedented success of modern Recurrent Neural Networks (RNNs) on learning tasks which involve sequential data, is their ability to model intricate long-term temporal dependencies. However, a well established measure of RNNs long-term memory capacity is lacking, and thus formal understanding of the effect of depth on their ability to correlate data throughout time is limited. Specifically, existing depth efficiency results on convolutional networks do not suffice in order to account for the success of deep RNNs on data of varying lengths. In order to address t…
