We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a special case. This conceptually simple move has two main advantages. First, it allows the learner to combat training data sparsity by allowing it to model words (or more generally, output symbols) as complex combinations of attributes without requiring that each combination is directly observed in the training data (as the softmax does). Second, it permits the inclusion of flexible prior knowledge in the form of a priori specified modular features, where the neural network component learns to dynamically control the weights of a log-linear distribution exploiting these features.
We conduct experiments in the domain of language modelling of French, that exploit morphological prior knowledge and show an important decrease in perplexity relative to a baseline RNN.
We provide other motivating iillustrations, and finally argue that the log-linear and the neural-network components contribute complementary strengths to the LL-RNN: the LL aspect allows the model to incorporate rich prior knowledge, while the NN aspect, according to the "representation learning" paradigm, allows the model to discover novel combination of characteristics.
The Chinese University of Hong Kong（香港中文大学）；Microsoft Research（微软研究院）
Recurrent Neural Networks (RNNs) have become increasingly popular for the task of language understanding. In this task, a semantic tagger is deployed to associate a semantic label to each word in an input sequence. The success of RNN may be attributed to its ability to memorize long-term dependence that relates the current-time semantic label prediction to the observations many time instances away. However, the memory capacity of simple RNNs is limited because of the gradient vanishing and exploding problem. We propose to use an external memory to improve memorization capability of RNNs. We co…
Episodic Memory Theory for the Mechanistic Interpretation of Recurrent Neural Networks
Manning College of Information and Computer Sciences（曼宁信息与计算机科学学院）；University of Massachusetts（马萨诸塞大学）；Department of Mathematics and Statistics（数学与统计系）
In this paper, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all recurrently fed to the hidden layers as feedback through different weighted paths. By extending the popular recurrent structure in RNNs, we provide the models with better short-term memory mechanism to learn long term dependency in sequences. Analogous to digital filters in signal processing, we call these structures as higher order RNNs (HORNNs). Similar to …
Carnegie Mellon University（卡内基梅隆大学）；Massachusetts Institute of Technology（麻省理工学院）
It is widely believed that the practical success of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) owes to the fact that CNNs and RNNs use a more compact parametric representation than their Fully-Connected Neural Network (FNN) counterparts, and consequently require fewer training examples to accurately estimate their parameters. We initiate the study of rigorously characterizing the sample-complexity of estimating CNNs and RNNs. We show that the sample-complexity to learn CNNs and RNNs scales linearly with their intrinsic dimension and this sample-complexity is much…
Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to input warping, and the ability to access contextual information, are also desirable in multidimensional domains. However, there has so far been no direct way of applying RNNs to data with more than one spatio-temporal dimension. This paper introduces multi-dimensional recurrent neural networks (MDRNNs), thereby extending the potential applicability of RNNs to…
This paper presents a new algorithm, Evolutionary eXploration of Augmenting Memory Models (EXAMM), which is capable of evolving recurrent neural networks (RNNs) using a wide variety of memory structures, such as Delta-RNN, GRU, LSTM, MGU and UGRNN cells. EXAMM evolved RNNs to perform prediction of large-scale, real world time series data from the aviation and power industries. These data sets consist of very long time series (thousands of readings), each with a large number of potentially correlated and dependent parameters. Four different parameters were selected for prediction and EXAMM runs…
Recurrent Neural Networks (RNNs) are used in state-of-the-art models in domains such as speech recognition, machine translation, and language modelling. Sparsity is a technique to reduce compute and memory requirements of deep learning models. Sparse RNNs are easier to deploy on devices and high-end server processors. Even though sparse operations need less compute and memory relative to their dense counterparts, the speed-up observed by using sparse operations is less than expected on different hardware platforms. In order to address this issue, we investigate two different approaches to indu…
This work aims at shedding some light on connections between finite state machines (FSMs), and recurrent neural networks (RNNs). Examined connections in this master's thesis is threefold: the extractability of finite state machines from recurrent neural networks, learnability aspects and computationnal links. With respect to the former, the long-standing clustering hypothesis of RNN hidden state space when trained to recognize regular languages was explored, and new insights into this hypothesis through the lens of recent advances of the generalization theory of Deep Learning are provided. As …
We study the privacy implications of training recurrent neural networks (RNNs) with sensitive training datasets. Considering membership inference attacks (MIAs), which aim to infer whether or not specific data records have been used in training a given machine learning model, we provide empirical evidence that a neural network's architecture impacts its vulnerability to MIAs. In particular, we demonstrate that RNNs are subject to a higher attack accuracy than feed-forward neural network (FFNN) counterparts. Additionally, we study the effectiveness of two prominent mitigation methods for preemp…
Simon Fraser University（西蒙弗雷泽大学）；Forschungszentrum Jülich GmbH（于利希研究中心有限公司）
The presented work demonstrates the training of recurrent neural networks (RNNs) from distributions of atom coordinates in solid state structures that were obtained using ab initio molecular dynamics (AIMD) simulations. AIMD simulations on solid state structures are treated as a multi-variate time-series problem. By referring interactions between atoms over the simulation time to temporary correlations among them, RNNs find patterns in the multi-variate time-dependent data, which enable forecasting trajectory paths and potential energy profiles. Two types of RNNs, namely gated recurrent unit a…
Due to the success of deep learning (DL) and its growing job market, students and researchers from many areas are interested in learning about DL technologies. Visualization has proven to be of great help during this learning process. While most current educational visualizations are targeted towards one specific architecture or use case, recurrent neural networks (RNNs), which are capable of processing sequential data, are not covered yet. This is despite the fact that tasks on sequential data, such as text and function analysis, are at the forefront of DL research. Therefore, we propose expl…
Recurrent Neural Networks (RNN), particularly Long Short Term Memory (LSTM) RNNs, are a popular and very successful method for learning and generating sequences. However, current generative RNN techniques do not allow real-time interactive control of the sequence generation process, thus aren't well suited for live creative expression. We propose a method of real-time continuous control and 'steering' of sequence generation using an ensemble of RNNs and dynamically altering the mixture weights of the models. We demonstrate the method using character based LSTM networks and a gestural interface…
Future of Humanity Institute, University of Oxford（牛津大学人类未来研究所）
Recurrent neural networks (RNNs) are widely used to model sequential data but their non-linear dependencies between sequence elements prevent parallelizing training over sequence length. We show the training of RNNs with only linear sequential dependencies can be parallelized over the sequence length using the parallel scan algorithm, leading to rapid training on long sequences even with small minibatch size. We develop a parallel linear recurrence CUDA kernel and show that it can be applied to immediately speed up training and inference of several state of the art RNN architectures by up to 9…
University of California, Santa Cruz（加州大学圣克鲁兹分校）；University of California, Irvine（加州大学欧文分校）；Columbia University（哥伦比亚大学）
Recurrent Neural Networks (RNNs) frequently exhibit complicated dynamics, and their sensitivity to the initialization process often renders them notoriously hard to train. Recent works have shed light on such phenomena analyzing when exploding or vanishing gradients may occur, either of which is detrimental for training dynamics. In this paper, we point to a formal connection between RNNs and chaotic dynamical systems and prove a qualitatively stronger phenomenon about RNNs than what exploding gradients seem to suggest. Our main result proves that under standard initialization (e.g., He, Xavie…
New York University（纽约大学）；Facebook AI Research（Facebook人工智能研究院）
Although RNNs have been shown to be powerful tools for processing sequential data, finding architectures or optimization strategies that allow them to model very long term dependencies is still an active area of research. In this work, we carefully analyze two synthetic datasets originally outlined in (Hochreiter and Schmidhuber, 1997) which are used to evaluate the ability of RNNs to store information over many time steps. We explicitly construct RNN solutions to these problems, and using these constructions, illuminate both the problems themselves and the way in which RNNs store different ty…
Similar to convolution neural networks, recurrent neural networks (RNNs) typically suffer from over-parameterization. Quantizing bit-widths of weights and activations results in runtime efficiency on hardware, yet it often comes at the cost of reduced accuracy. This paper proposes a quantization approach that increases model size with bit-width reduction. This approach will allow networks to perform at their baseline accuracy while still maintaining the benefits of reduced precision and overall model size reduction.
HadamRNN: Binary and Sparse Ternary Orthogonal RNNs
Institut de Mathématiques de Toulouse（图卢兹数学研究所）；Institut de Recherche Technologique Saint Exupéry（圣埃克苏佩里技术研究所）；Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）
Central Pattern Generators (CPGs) are biological neural circuits capable of producing coordinated rhythmic outputs in the absence of rhythmic input. As a result, they are responsible for most rhythmic motion in living organisms. This rhythmic control is broadly applicable to fields such as locomotive robotics and medical devices. In this paper, we explore the possibility of creating a self-sustaining CPG network for reinforcement learning that learns rhythmic motion more efficiently and across more general environments than the current multilayer perceptron (MLP) baseline models. Recent work i…
Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to very long sequences. This paper proposes a simple method that improves the ability to capture long term dependencies in RNNs by adding an unsupervised auxiliary loss to the original objective. This auxiliary loss forces RNNs to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences a…
