In this work, we present a machine learning approach for reducing the error when numerically solving time-dependent partial differential equations (PDE). We use a fully convolutional LSTM network to exploit the spatiotemporal dynamics of PDEs. The neural network serves to enhance finite-difference and finite-volume methods (FDM/FVM) that are commonly used to solve PDEs, allowing us to maintain guarantees on the order of convergence of our method. We train the network on simulation data, and show that our network can reduce error by a factor of 2 to 3 compared to the baseline algorithms. We demonstrate our method on three PDEs that each feature qualitatively different dynamics. We look at the linear advection equation, which propagates its initial conditions at a constant speed, the inviscid Burgers' equation, which develops shockwaves, and the Kuramoto-Sivashinsky (KS) equation, which is chaotic.
Fully convolutional neural networks (FCN) have been shown to achieve state-of-the-art performance on the task of classifying time series sequences. We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification. Our proposed models significantly enhance the performance of fully convolutional networks with a nominal increase in model size and require minimal preprocessing of the dataset. The proposed Long Short Term Memory Fully Convolutional Network (LSTM-FCN) achieves state-of-the-art perfo…
Long Short Term Memory Fully Convolutional Neural Networks (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (UCR) time series repository. However, there has been no study on why LSTM-FCN and ALSTM-FCN perform well. In this paper, we perform a series of ablation tests (3627 experiments) on LSTM-FCN and ALSTM-FCN to provide a better understanding of the model and each of its sub-module. Results from the ablation tests on ALSTM-FCN and LSTM-FCN show that the…
Hybrid LSTM-fully convolutional networks (LSTM-FCN) for time series classification have produced state-of-the-art classification results on univariate time series. We show that replacing the LSTM with a gated recurrent unit (GRU) to create a GRU-fully convolutional network hybrid model (GRU-FCN) can offer even better performance on many time series datasets. The proposed GRU-FCN model outperforms state-of-the-art classification performance in many univariate and multivariate time series datasets. In addition, since the GRU uses a simpler architecture than the LSTM, it has fewer training parame…
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…
School of Information Technology, University of Cincinnati（辛辛那提大学信息技术学院）；School of Computing and Informatics, University of Louisiana at Lafayette（路易斯安那大学拉法叶分校计算与信息学院）
Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM(rgcLSTM) architecture that requires a significantly lower parameter budget than a comparable convLSTM. By using a single multi-function gate, our reduced-gate model achieves equal or better next-frame(s) prediction accuracy than the original convolutional LSTM while using a smaller parameter budget, there…
University of Maryland（马里兰大学）；NVIDIA Research（英伟达研究院）
Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation.However, existing methods still perform poorly on challenging video tasks such as long-term forecasting. This is because these kinds of challenging tasks require learning long-term spatio-temporal correlations in the video sequence. In this paper, we propose a higher-order convolutional LSTM model that can efficiently learn these correlations, along with a succinct representations of the history. This is accomplished through a novel tensor tra…
Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multiv…
Kavli IPMU (WPI), University of Tokyo（东京大学卡弗里数物连携宇宙研究机构（世界顶级国际研究中心））
In this work we propose a novel approach to utilize convolutional neural networks for time series forecasting. The time direction of the sequential data with spatial dimensions $D=1,2$ is considered democratically as the input of a spatiotemporal $(D+1)$-dimensional convolutional neural network. Latter then reduces the data stream from $D +1 \to D$ dimensions followed by an incriminator cell which uses this information to forecast the subsequent time step. We empirically compare this strategy to convolutional LSTM's and LSTM's on their performance on the sequential MNIST and the JSB chorals da…
Public Transport Movia（莫维亚公共交通公司）；Technical University of Denmark（丹麦技术大学）
Accurate and reliable travel time predictions in public transport networks are essential for delivering an attractive service that is able to compete with other modes of transport in urban areas. The traditional application of this information, where arrival and departure predictions are displayed on digital boards, is highly visible in the city landscape of most modern metropolises. More recently, the same information has become critical as input for smart-phone trip planners in order to alert passengers about unreachable connections, alternative route choices and prolonged travel times. More…
Reliable 4D aircraft trajectory prediction, whether in a real-time setting or for analysis of counterfactuals, is important to the efficiency of the aviation system. Toward this end, we first propose a highly generalizable efficient tree-based matching algorithm to construct image-like feature maps from high-fidelity meteorological datasets - wind, temperature and convective weather. We then model the track points on trajectories as conditional Gaussian mixtures with parameters to be learned from our proposed deep generative model, which is an end-to-end convolutional recurrent neural network …
Whiting School of Engineering, Johns Hopkins University（约翰斯·霍普金斯大学工学院）；Princeton University（普林斯顿大学）；The Department of Chemical and Biological Engineering（化工与生物工程系）；Department of Chemical and Biomolecular Engineering（化学与生物分子工程系）
We present an approach, based on learning an intrinsic data manifold, for the initialization of the internal state values of LSTM recurrent neural networks, ensuring consistency with the initial observed input data. Exploiting the generalized synchronization concept, we argue that the converged, "mature" internal states constitute a function on this learned manifold. The dimension of this manifold then dictates the length of observed input time series data required for consistent initialization. We illustrate our approach through a partially observed chemical model system, where initializing t…
We present a new convolutional neural network-based time-series model. Typical convolutional neural network (CNN) architectures rely on the use of max-pooling operators in between layers, which leads to reduced resolution at the top layers. Instead, in this work we consider a fully convolutional network (FCN) architecture that uses causal filtering operations, and allows for the rate of the output signal to be the same as that of the input signal. We furthermore propose an undecimated version of the FCN, which we refer to as the undecimated fully convolutional neural network (UFCNN), and is mo…
Action recognition greatly benefits motion understanding in video analysis. Recurrent networks such as long short-term memory (LSTM) networks are a popular choice for motion-aware sequence learning tasks. Recently, a convolutional extension of LSTM was proposed, in which input-to-hidden and hidden-to-hidden transitions are modeled through convolution with a single kernel. This implies an unavoidable trade-off between effectiveness and efficiency. Herein, we propose a new enhancement to convolutional LSTM networks that supports accommodation of multiple convolutional kernels and layers. This re…
This paper explores the use of convolution LSTMs to simultaneously learn spatial- and temporal-information in videos. A deep network of convolutional LSTMs allows the model to access the entire range of temporal information at all spatial scales of the data. We describe our experiments involving convolution LSTMs for lipreading that demonstrate the model is capable of selectively choosing which spatiotemporal scales are most relevant for a particular dataset. The proposed deep architecture also holds promise in other applications where spatiotemporal features play a vital role without having t…
We consider the problem of predicting semantic segmentation of future frames in a video. Given several observed frames in a video, our goal is to predict the semantic segmentation map of future frames that are not yet observed. A reliable solution to this problem is useful in many applications that require real-time decision making, such as autonomous driving. We propose a novel model that uses convolutional LSTM (ConvLSTM) to encode the spatiotemporal information of observed frames for future prediction. We also extend our model to use bidirectional ConvLSTM to capture temporal information in…
The University of Arizona（亚利桑那大学）；Massachusetts Institute of Technology（麻省理工学院）
This study presents a novel unsupervised convolutional Neural Network (NN) architecture with nonlocal interactions for solving Partial Differential Equations (PDEs). The nonlocal Peridynamic Differential Operator (PDDO) is employed as a convolutional filter for evaluating derivatives the field variable. The NN captures the time-dynamics in smaller latent space through encoder-decoder layers with a Convolutional Long-short Term Memory (ConvLSTM) layer between them. The ConvLSTM architecture is modified by employing a novel activation function to improve the predictive capability of the learning…
Phase unwrapping is a classical ill-posed problem which aims to recover the true phase from wrapped phase. In this paper, we introduce a novel Convolutional Neural Network (CNN) that incorporates a Spatial Quad-Directional Long Short Term Memory (SQD-LSTM) for phase unwrapping, by formulating it as a regression problem. Incorporating SQD-LSTM can circumvent the typical CNNs' inherent difficulty of learning global spatial dependencies which are vital when recovering the true phase. Furthermore, we employ a problem specific composite loss function to train this network. The proposed network is f…
Microsoft Corporation（微软公司）；Microsoft Turing（微软图灵）
We present the encoder-forecaster convolutional long short-term memory (LSTM) deep-learning model that powers Microsoft Weather's operational precipitation nowcasting product. This model takes as input a sequence of weather radar mosaics and deterministically predicts future radar reflectivity at lead times up to 6 hours. By stacking a large input receptive field along the feature dimension and conditioning the model's forecaster with predictions from the physics-based High Resolution Rapid Refresh (HRRR) model, we are able to outperform optical flow and HRRR baselines by 20-25% on multiple me…
Case Western Reserve University（凯斯西储大学）；IBM Almaden Research Center（IBM阿尔马登研究中心）
We explore a solution for learning disease signatures from weakly, yet easily obtainable, annotated volumetric medical imaging data by analyzing 3D volumes as a sequence of 2D images. We demonstrate the performance of our solution in the detection of emphysema in lung cancer screening low-dose CT images. Our approach utilizes convolutional long short-term memory (LSTM) to "scan" sequentially through an imaging volume for the presence of disease in a portion of scanned region. This framework allowed effective learning given only volumetric images and binary disease labels, thus enabling trainin…
Financial markets are a complex dynamical system. The complexity comes from the interaction between a market and its participants, in other words, the integrated outcome of activities of the entire participants determines the markets trend, while the markets trend affects activities of participants. These interwoven interactions make financial markets keep evolving. Inspired by stochastic recurrent models that successfully capture variability observed in natural sequential data such as speech and video, we propose CLVSA, a hybrid model that consists of stochastic recurrent networks, the sequen…
University of Louisiana at Lafayette（路易斯安那大学拉斐特分校）
The problem of video frame prediction has received much interest due to its relevance to many computer vision applications such as autonomous vehicles or robotics. Supervised methods for video frame prediction rely on labeled data, which may not always be available. In this paper, we provide a novel unsupervised deep-learning method called Inception-based LSTM for video frame prediction. The general idea of inception networks is to implement wider networks instead of deeper networks. This network design was shown to improve the performance of image classification. The proposed method is evalua…
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；University of Michigan（密歇根大学）；Columbia University in the City of New York（纽约哥伦比亚大学）；National University of Defense Technology（国防科技大学）
A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements. This study tackles speaker-dependent tongue motion prediction problem in unlabeled ultrasound videos with convolutional long short-term memory (ConvLSTM) networks. The model has been tested on two different ultrasound corpora. ConvLSTM outperforms 3-dimensional convolutional neural network (3DCNN) in predicting the 9\textsuperscript{th} frames based on 8 preceding frames, and also demonstrates good capacity to predict only the tongue contours in future frames. Furth…
Clouds frequently cover the Earth's surface and pose an omnipresent challenge to optical Earth observation methods. The vast majority of remote sensing approaches either selectively choose single cloud-free observations or employ a pre-classification strategy to identify and mask cloudy pixels. We follow a different strategy and treat cloud coverage as noise that is inherent to the observed satellite data. In prior work, we directly employed a straightforward \emph{convolutional long short-term memory} network for vegetation classification without explicit cloud filtering and achieved state-of…
This paper presents an engine able to forecast jointly the concentrations of the main pollutants harming people's health: nitrogen dioxyde (NO2), ozone (O3) and particulate matter (PM2.5 and PM10, which are respectively the particles whose diameters are below 2.5 um and 10 um respectively). The forecasts are performed on a regular grid (the results presented in the paper are produced with a 0.5° resolution grid over Europe and the United States) with a neural network whose architecture includes convolutional LSTM blocks. The engine is fed with the most recent air quality monitoring stations me…
Hong Kong University of Science and Technology（香港科技大学）
Tactile sensing is essential to the human perception system, so as to robot. In this paper, we develop a novel optical-based tactile sensor "FingerVision" with effective signal processing algorithms. This sensor is composed of soft skin with embedded marker array bonded to rigid frame, and a web camera with a fisheye lens. While being excited with contact force, the camera tracks the movements of markers and deformation field is obtained. Compared to existing tactile sensors, our sensor features compact footprint, high resolution, and ease of fabrication. Besides, utilizing the deformation fie…
Deep learning models utilizing convolution layers have achieved state-of-the-art performance on univariate time series classification tasks. In this work, we propose improving CNN based time series classifiers by utilizing Octave Convolutions (OctConv) to outperform themselves. These network architectures include Fully Convolutional Networks (FCN), Residual Neural Networks (ResNets), LSTM-Fully Convolutional Networks (LSTM-FCN), and Attention LSTM-Fully Convolutional Networks (ALSTM-FCN). The proposed layers significantly improve each of these models with minimally increased network parameters…
Indian Association for the Cultivation of Science（印度科学培育协会）
Development of new drugs is an expensive and time-consuming process. Due to the world-wide SARS-CoV-2 outbreak, it is essential that new drugs for SARS-CoV-2 are developed as soon as possible. Drug repurposing techniques can reduce the time span needed to develop new drugs by probing the list of existing FDA-approved drugs and their properties to reuse them for combating the new disease. We propose a novel architecture DeepGLSTM, which is a Graph Convolutional network and LSTM based method that predicts binding affinity values between the FDA-approved drugs and the viral proteins of SARS-CoV-2…
Fraunhofer FIT（弗劳恩霍夫应用信息技术研究所）；RWTH Aachen University（亚琛工业大学）；Insight SFI Research Centre for Data Analytics（Insight SFI数据分析研究中心）；Data Science Institute（数据科学研究所）；National University of Ireland Galway（爱尔兰国立大学戈尔韦分校）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices but also enables people to express anti-social behaviour like online harassment, cyberbullying, and hate speech. Numerous works have been proposed to utilize these data for social and anti-social behaviours analysis, document characterization, and sentiment analysis by predicting the contexts mostly for highly resourced languages such as English. However, there are languages that are under-resources, e.g., South Asian languages like Bengali, Tamil,…
The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network. However, the methods based the Bi-LSTM have some inherent drawbacks: hard to parallel computing, little efficient in applying the Dropout method to inhibit the Overfitting and little efficient in capturing the character information at the more distant site of a long sentence for the word segmentation task. In this work, we propose a sequence-to-sequence transformer model for Chinese word segmentation, which is premised a type of convolutional neural network named temporal convolutional network…
University of Amsterdam（阿姆斯特丹大学）；University of Edinburgh（爱丁堡大学）
Semantic role labeling (SRL) is the task of identifying the predicate-argument structure of a sentence. It is typically regarded as an important step in the standard NLP pipeline. As the semantic representations are closely related to syntactic ones, we exploit syntactic information in our model. We propose a version of graph convolutional networks (GCNs), a recent class of neural networks operating on graphs, suited to model syntactic dependency graphs. GCNs over syntactic dependency trees are used as sentence encoders, producing latent feature representations of words in a sentence. We obser…
Fraunhofer FIT（弗劳恩霍夫应用信息技术研究所）；RWTH Aachen University（亚琛工业大学）；University of Dhaka（达卡大学）
Interference between pharmacological substances can cause serious medical injuries. Correctly predicting so-called drug-drug interactions (DDI) does not only reduce these cases but can also result in a reduction of drug development cost. Presently, most drug-related knowledge is the result of clinical evaluations and post-marketing surveillance; resulting in a limited amount of information. Existing data-driven prediction approaches for DDIs typically rely on a single source of information, while using information from multiple sources would help improve predictions. Machine learning (ML) tech…
ADVA Optical Networking SE（ADVA光网络公司）；Christian-Albrechts-Universität zu Kiel（基尔大学）
A hybrid prognostic model based on convolutional neural networks (CNN) and long short-term memory (LSTM) is proposed to predict the laser remaining useful life (RUL). The experimental results show that it outperforms the conventional methods.
As the climate changes, the severity of wildland fires is expected to worsen. Models that accurately capture fire propagation dynamics greatly help efforts for understanding, responding to and mitigating the damages caused by these fires. Machine learning techniques provide a potential approach for developing such models. The objective of this study is to evaluate the feasibility of using a Convolutional Long Short-Term Memory (ConvLSTM) recurrent neural network to model the dynamics of wildland fire propagation. The machine learning model is trained on simulated wildfire data generated by a m…
There exist several data-driven approaches that enable us model time series data including traditional regression-based modeling approaches (i.e., ARIMA). Recently, deep learning techniques have been introduced and explored in the context of time series analysis and prediction. A major research question to ask is the performance of these many variations of deep learning techniques in predicting time series data. This paper compares two prominent deep learning modeling techniques. The Recurrent Neural Network (RNN)-based Long Short-Term Memory (LSTM) and the convolutional Neural Network (CNN)-b…
University of Edinburgh（爱丁堡大学）；Microsoft Research（微软研究院）；UC Irvine（加州大学尔湾分校）；University of Washington（华盛顿大学）；University of Alberta（阿尔伯塔大学）
We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs. First, we show that a deep CNN with an architecture inspired by the models recently introduced in image recognition can yield better accuracy than previous convolutional and LSTM networks on the standard 309h Switchboard automatic speech recognition task. Then we show that even more accurate CNNs can be trained under the guidance of LSTMs using a variant of model compression, which we call model blending because the teacher and student models are si…
Islamic University of Technology（伊斯兰科技大学）；Data61-CSIRO（澳大利亚联邦科学与工业研究组织数据61中心）
Automatically detecting violence from surveillance footage is a subset of activity recognition that deserves special attention because of its wide applicability in unmanned security monitoring systems, internet video filtration, etc. In this work, we propose an efficient two-stream deep learning architecture leveraging Separable Convolutional LSTM (SepConvLSTM) and pre-trained MobileNet where one stream takes in background suppressed frames as inputs and other stream processes difference of adjacent frames. We employed simple and fast input pre-processing techniques that highlight the moving o…
Internet of Things (IoT) allowed smart homes to improve the quality and the comfort of our daily lives. However, these conveniences introduced several security concerns that increase rapidly. IoT devices, smart home hubs, and gateway raise various security risks. The smart home gateways act as a centralized point of communication between the IoT devices, which can create a backdoor into network data for hackers. One of the common and effective ways to detect such attacks is intrusion detection in the network traffic. In this paper, we proposed an intrusion detection system (IDS) to detect anom…
Institut für Medizinische Informatik der Universität zu Lübeck（吕贝克大学医学信息学研究所）；Universität zu Lübeck（吕贝克大学）；INSERM（法国国家健康与医学研究院）
For the weakly supervised task of electrocardiogram (ECG) rhythm classification, convolutional neural networks (CNNs) and long short-term memory (LSTM) networks are two increasingly popular classification models. This work investigates whether a combination of both architectures to so-called convolutional long short-term memory (ConvLSTM) networks can improve classification performances by explicitly capturing morphological as well as temporal features of raw ECG records. In addition, various attention mechanisms are studied to localize and visualize record sections of abnormal morphology and …
The Ubicomp Digital 2020 -- Time Series Classification Challenge from STABILO is a challenge about multi-variate time series classification. The data collected from 100 volunteer writers, and contains 15 features measured with multiple sensors on a pen. In this paper,we use a neural network to classify the data into 52 classes, that is lower and upper cases of Arabic letters. The proposed architecture of the neural network a is CNN-LSTM network. It combines convolutional neural network (CNN) for short term context with along short term memory layer (LSTM) for also long term dependencies. We re…
A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a neural network architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a kernel reminiscent of a convolutional kernel. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music. Link to the code is provided.
University Hospital of Strasbourg（斯特拉斯堡大学医院）；IRCAD（法国消化外科研究所）；IHU Strasbourg（斯特拉斯堡大学医院研究所）；ICube（斯特拉斯堡计算机与图像科学实验室）；University of Strasbourg（斯特拉斯堡大学）；CNRS（法国国家科学研究中心）
Purpose: Real-time surgical tool tracking is a core component of the future intelligent operating room (OR), because it is highly instrumental to analyze and understand the surgical activities. Current methods for surgical tool tracking in videos need to be trained on data in which the spatial positions of the tools are manually annotated. Generating such training data is difficult and time-consuming. Instead, we propose to use solely binary presence annotations to train a tool tracker for laparoscopic videos. Methods: The proposed approach is composed of a CNN + Convolutional LSTM (ConvLSTM) …
The FloatSD technology has been shown to have excellent performance on low-complexity convolutional neural networks (CNNs) training and inference. In this paper, we applied FloatSD to recurrent neural networks (RNNs), specifically long short-term memory (LSTM). In addition to FloatSD weight representation, we quantized the gradients and activations in model training to 8 bits. Moreover, the arithmetic precision for accumulations and the master copy of weights were reduced from 32 bits to 16 bits. We demonstrated that the proposed training scheme can successfully train several LSTM models from …
Projection of changes in extreme indices of climate variables such as temperature and precipitation are critical to assess the potential impacts of climate change on human-made and natural systems, including critical infrastructures and ecosystems. While impact assessment and adaptation planning rely on high-resolution projections (typically in the order of a few kilometers), state-of-the-art Earth System Models (ESMs) are available at spatial resolutions of few hundreds of kilometers. Current solutions to obtain high-resolution projections of ESMs include downscaling approaches that consider …
Solar energy is a clean and renewable energy. Photovoltaic (PV) power is an important way to utilize solar energy. Accurate PV power forecast is crucial to the large-scale application of PV power and the stability of electricity grid. This paper proposes a novel method for short-term photovoltaic power forecast using deep convolutional long short-term memory (ConvLSTM) network and kernel density estimation (KDE). In the proposed method, ConvLSTM is used to forecast the future photovoltaic power and KDE is used for estimating the joint probabilistic density function and giving the probabilistic…
In recent years, long short-term memory neural networks (LSTMs) have been applied quite successfully to problems in handwritten text recognition. However, their strength is more located in handling sequences of variable length than in handling geometric variability of the image patterns. Furthermore, the best results for LSTMs are often based on large-scale training of an ensemble of network instances. In this paper, an end-to-end convolutional LSTM Neural Network is used to handle both geometric variation and sequence variability. We show that high performances can be reached on a common benc…
The Long Short-Term Memory (LSTM) layer is an important advancement in the field of neural networks and machine learning, allowing for effective training and impressive inference performance. LSTM-based neural networks have been successfully employed in various applications such as speech processing and language translation. The LSTM layer can be simplified by removing certain components, potentially speeding up training and runtime with limited change in performance. In particular, the recently introduced variants, called SLIM LSTMs, have shown success in initial experiments to support this v…
Johannes Kepler University Linz（约翰内斯·开普勒大学林茨分校）；Google Research（谷歌研究院）；Institute of Advanced Research in Artificial Intelligence（人工智能高等研究院）
The success of Convolutional Neural Networks (CNNs) in computer vision is mainly driven by their strong inductive bias, which is strong enough to allow CNNs to solve vision-related tasks with random weights, meaning without learning. Similarly, Long Short-Term Memory (LSTM) has a strong inductive bias towards storing information over time. However, many real-world systems are governed by conservation laws, which lead to the redistribution of particular quantities -- e.g. in physical and economical systems. Our novel Mass-Conserving LSTM (MC-LSTM) adheres to these conservation laws by extending…
