DOCSLIB.ORG

Long Short-Term Memory 1 Introduction

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text

Load more

LONG SHORTTERM MEMORY Neural Computation J urgen Schmidhuber Sepp Ho chreiter IDSIA Fakultat f ur Informatik Corso Elvezia Technische Universitat M unchen Lugano Switzerland M unchen Germany juergenidsiach ho chreitinformatiktumuenchende httpwwwidsiachjuergen httpwwwinformatiktumuenchendehochreit Abstract Learning to store information over extended time intervals via recurrent backpropagation takes a very long time mostly due to insucient decaying error back ow We briey review Ho chreiters analysis of this problem then address it by introducing a novel ecient gradientbased metho d called Long ShortTerm Memory LSTM Truncating the gradient where this do es not do harm LSTM can learn to bridge minimal time lags in excess of discrete time steps by enforcing constant error ow through constant error carrousels within sp ecial units Multiplicative gate units learn to op en and close access to the constant error ow LSTM is lo cal in space and time its computational complexity p er time step and weight is O Our exp eriments with articial data involve lo cal distributed realvalued and noisy pattern representations In comparisons with RTRL BPTT Recurrent CascadeCorrelation Elman nets and Neural Sequence Chunking LSTM leads to many more successful runs and learns much faster LSTM also solves complex articial long time lag tasks that have never b een solved by previous recurrent network algorithms INTRODUCTION Recurrent networks can in principle use their feedback connections to store representations of recent input events in form of activations shortterm memory as opp osed to longterm mem ory embo died by slowly changing weights This is p otentially signicant for many applications including sp eech pro cessing nonMarkovian control and music comp osition eg Mozer The most widely used algorithms for learning what to put in shortterm memory however take to o much time or do not work well at all esp ecially when minimal time lags b etween inputs and corresp onding teacher signals are long Although theoretically fascinating existing metho ds do not provide clear practical advantages over say backprop in feedforward nets with limited time windows This pap er will review an analysis of the problem and suggest a remedy The problem With conventional BackPropagation Through Time BPTT eg Williams and Zipser Werbos or RealTime Recurrent Learning RTRL eg Robinson and Fallside error signals owing backwards in time tend to either blow up or vanish the temp oral evolution of the backpropagated error exp onentially dep ends on the size of the weights Ho chreiter Case may lead to oscillating weights while in case learning to bridge long time lags takes a prohibitive amount of time or do es not work at all see section The remedy This pap er presents Long ShortTerm Memory LSTM a novel recurrent network architecture in conjunction with an appropriate gradientbased learning algorithm LSTM is designed to overcome these error backow problems It can learn to bridge time intervals in excess of steps even in case of noisy incompressible input sequences without loss of short time lag capabilities This is achieved by an ecient gradientbased algorithm for an architecture enforcing constant thus neither explo ding nor vanishing error ow through internal states of sp ecial units provided the gradient computation is truncated at certain architecturespecic p oints this do es not aect longterm error ow though Outline of pap er Section will briey review previous work Section b egins with an outline of the detailed analysis of vanishing errors due to Ho chreiter It will then introduce a naive approach to constant error backprop for didactic purp oses and highlight its problems concerning information storage and retrieval These problems will lead to the LSTM architecture as describ ed in Section Section will present numerous exp eriments and comparisons with comp eting metho ds LSTM outp erforms them and also learns to solve complex articial tasks no other recurrent net algorithm has solved Section will discuss LSTMs limitations and advantages The app endix contains a detailed description of the algorithm A and explicit error ow formulae A PREVIOUS WORK This section will fo cus on recurrent nets with timevarying inputs as opp osed to nets with sta tionary inputs and xp ointbased gradient calculations eg Almeida Pineda Gradientdescent variants The approaches of Elman Fahlman Williams Schmidhuber a Pearlmutter and many of the related algorithms in Pearl mutters comprehensive overview suer from the same problems as BPTT and RTRL see Sections and Timedelays Other metho ds that seem practical for short time lags only are TimeDelay Neural Networks Lang et al and Plates metho d Plate which up dates unit activa tions based on a weighted sum of old activations see also de Vries and Princip e Lin et al prop ose variants of timedelay networks called NARX networks Time constants To deal with long time lags Mozer uses time constants inuencing changes of unit activations deVries and Princip es ab ovementioned approach may in fact b e viewed as a mixture of TDNN and time constants For long time lags however the time constants need external ne tuning Mozer Sun et als alternative approach up dates the activation of a recurrent unit by adding the old activation and the scaled current net input The net input however tends to p erturb the stored information which makes longterm storage impractical Rings approach Ring also prop osed a metho d for bridging long time lags Whenever a unit in his network receives conicting error signals he adds a higher order unit inuencing appropriate connections Although his approach can sometimes b e extremely fast to bridge a time lag involving steps may require the addition of units Also Rings net do es not generalize to unseen lag durations Bengio et als approaches Bengio et al investigate metho ds such as simulated annealing multigrid random search timeweighted pseudoNewton optimization and discrete error propagation Their latch and sequence problems are very similar to problem a with minimal time lag see Exp eriment Bengio and Frasconi also prop ose an EM approach for propagating targets With n socalled state networks at a given time their system can b e in one of only n dierent states See also b eginning of Section But to solve continuous problems such as the adding problem Section their system would require an unacceptable number of states ie state networks Kalman lters Puskorius and Feldkamp use Kalman lter techniques to improve recurrent net p erformance Since they use a derivative discount factor imp osed to decay exp o nentially the eects of past dynamic derivatives there is no reason to b elieve that their Kalman Filter Trained Recurrent Networks will b e useful for very long minimal time lags Second order nets We will see that LSTM uses multiplicative units MUs to protect error ow from unwanted p erturbations It is not the rst recurrent net metho d using MUs though For instance Watrous and Kuhn use MUs in second order nets Some dierences to LSTM are Watrous and Kuhns architecture do es not enforce constant error ow and is not designed to solve long time lag problems It has fully connected secondorder sigmapi units while the LSTM architectures MUs are used only to gate access to constant error ow Watrous and Kuhns algorithm costs O W op erations p er time step ours only O W where W is the number of weights See also Miller and Giles for additional work on MUs Simple weight guessing To avoid long time lag problems of gradientbased approaches we may simply randomly initialize all network weights until the resulting net happ ens to classify all training sequences correctly In fact recently we discovered Schmidhuber and Ho chreiter Ho chreiter and Schmidhuber that simple weight guessing solves many of the problems in Bengio Bengio and Frasconi Miller and Giles Lin et al faster than the algorithms prop osed therein This do es not mean that weight guessing is a go o d algorithm It just means that the problems are very simple More realistic tasks require either many free parameters eg input weights or high weight precision eg for continuousvalued parameters such that guessing b ecomes completely infeasible Adaptive sequence chunkers Schmidhubers hierarchical chunker systems b do have a capability to bridge arbitrary time lags but only if there is lo cal predictability across the subsequences causing the time lags see also Mozer For instance in his p ostdo ctoral thesis Schmidhuber uses hierarchical recurrent nets to rapidly solve certain grammar learning tasks involving minimal time lags in excess of steps The p erformance of chunker systems however deteriorates as the noise level increases and the input sequences b ecome less compressible LSTM do es not suer from this problem CONSTANT ERROR BACKPROP EXPONENTIALLY DECAYING ERROR Conventional BPTT eg Williams and Zipser Output unit k s target at time t is denoted by d t Using mean squared error k s error signal is k k 0 net td t y t t f k k k k where i y t f net t i i is the activation of a noninput unit i with dierentiable activation function f i X j net t w y t i ij j is unit is current net input and w is the weight on the connection from unit j to i Some ij nonoutput unit j s backpropagated error signal is X 0 t f net t w t j j ij i j i l The corresp onding contribution to w s total weight up date is ty t where is the j l j learning rate and l stands for an arbitrary unit connected to unit j Outline of
Recommended publications
  • Backpropagation and Deep Learning in the Brain

    Backpropagation and Deep Learning in the Brain

    Backpropagation and Deep Learning in the Brain Simons Institute -- Computational Theories of the Brain 2018 Timothy Lillicrap DeepMind, UCL With: Sergey Bartunov, Adam Santoro, Jordan Guerguiev, Blake Richards, Luke Marris, Daniel Cownden, Colin Akerman, Douglas Tweed, Geoffrey Hinton The “credit assignment” problem The solution in artificial networks: backprop Credit assignment by backprop works well in practice and shows up in virtually all of the state-of-the-art supervised, unsupervised, and reinforcement learning algorithms. Why Isn’t Backprop “Biologically Plausible”? Why Isn’t Backprop “Biologically Plausible”? Neuroscience Evidence for Backprop in the Brain? A spectrum of credit assignment algorithms: A spectrum of credit assignment algorithms: A spectrum of credit assignment algorithms: How to convince a neuroscientist that the cortex is learning via [something like] backprop - To convince a machine learning researcher, an appeal to variance in gradient estimates might be enough. - But this is rarely enough to convince a neuroscientist. - So what lines of argument help? How to convince a neuroscientist that the cortex is learning via [something like] backprop - What do I mean by “something like backprop”?: - That learning is achieved across multiple layers by sending information from neurons closer to the output back to “earlier” layers to help compute their synaptic updates. How to convince a neuroscientist that the cortex is learning via [something like] backprop 1. Feedback connections in cortex are ubiquitous and modify the
  • Training Autoencoders by Alternating Minimization

    Training Autoencoders by Alternating Minimization

    Under review as a conference paper at ICLR 2018 TRAINING AUTOENCODERS BY ALTERNATING MINI- MIZATION Anonymous authors Paper under double-blind review ABSTRACT We present DANTE, a novel method for training neural networks, in particular autoencoders, using the alternating minimization principle. DANTE provides a distinct perspective in lieu of traditional gradient-based backpropagation techniques commonly used to train deep networks. It utilizes an adaptation of quasi-convex optimization techniques to cast autoencoder training as a bi-quasi-convex optimiza- tion problem. We show that for autoencoder configurations with both differentiable (e.g. sigmoid) and non-differentiable (e.g. ReLU) activation functions, we can perform the alternations very effectively. DANTE effortlessly extends to networks with multiple hidden layers and varying network configurations. In experiments on standard datasets, autoencoders trained using the proposed method were found to be very promising and competitive to traditional backpropagation techniques, both in terms of quality of solution, as well as training speed. 1 INTRODUCTION For much of the recent march of deep learning, gradient-based backpropagation methods, e.g. Stochastic Gradient Descent (SGD) and its variants, have been the mainstay of practitioners. The use of these methods, especially on vast amounts of data, has led to unprecedented progress in several areas of artificial intelligence. On one hand, the intense focus on these techniques has led to an intimate understanding of hardware requirements and code optimizations needed to execute these routines on large datasets in a scalable manner. Today, myriad off-the-shelf and highly optimized packages exist that can churn reasonably large datasets on GPU architectures with relatively mild human involvement and little bootstrap effort.
  • Q-Learning in Continuous State and Action Spaces

    Q-Learning in Continuous State and Action Spaces

    -Learning in Continuous Q State and Action Spaces Chris Gaskett, David Wettergreen, and Alexander Zelinsky Robotic Systems Laboratory Department of Systems Engineering Research School of Information Sciences and Engineering The Australian National University Canberra, ACT 0200 Australia [cg dsw alex]@syseng.anu.edu.au j j Abstract. -learning can be used to learn a control policy that max- imises a scalarQ reward through interaction with the environment. - learning is commonly applied to problems with discrete states and ac-Q tions. We describe a method suitable for control tasks which require con- tinuous actions, in response to continuous states. The system consists of a neural network coupled with a novel interpolator. Simulation results are presented for a non-holonomic control task. Advantage Learning, a variation of -learning, is shown enhance learning speed and reliability for this task.Q 1 Introduction Reinforcement learning systems learn by trial-and-error which actions are most valuable in which situations (states) [1]. Feedback is provided in the form of a scalar reward signal which may be delayed. The reward signal is defined in relation to the task to be achieved; reward is given when the system is successfully achieving the task. The value is updated incrementally with experience and is defined as a discounted sum of expected future reward. The learning systems choice of actions in response to states is called its policy. Reinforcement learning lies between the extremes of supervised learning, where the policy is taught by an expert, and unsupervised learning, where no feedback is given and the task is to find structure in data.
  • CS 189 Introduction to Machine Learning Spring 2021 Jonathan Shewchuk HW6

    CS 189 Introduction to Machine Learning Spring 2021 Jonathan Shewchuk HW6

    CS 189 Introduction to Machine Learning Spring 2021 Jonathan Shewchuk HW6 Due: Wednesday, April 21 at 11:59 pm Deliverables: 1. Submit your predictions for the test sets to Kaggle as early as possible. Include your Kaggle scores in your write-up (see below). The Kaggle competition for this assignment can be found at • https://www.kaggle.com/c/spring21-cs189-hw6-cifar10 2. The written portion: • Submit a PDF of your homework, with an appendix listing all your code, to the Gradescope assignment titled “Homework 6 Write-Up”. Please see section 3.3 for an easy way to gather all your code for the submission (you are not required to use it, but we would strongly recommend using it). • In addition, please include, as your solutions to each coding problem, the specific subset of code relevant to that part of the problem. Whenever we say “include code”, that means you can either include a screenshot of your code, or typeset your code in your submission (using markdown or LATEX). • You may typeset your homework in LaTeX or Word (submit PDF format, not .doc/.docx format) or submit neatly handwritten and scanned solutions. Please start each question on a new page. • If there are graphs, include those graphs in the correct sections. Do not put them in an appendix. We need each solution to be self-contained on pages of its own. • In your write-up, please state with whom you worked on the homework. • In your write-up, please copy the following statement and sign your signature next to it.
  • Double Backpropagation for Training Autoencoders Against Adversarial Attack

    Double Backpropagation for Training Autoencoders Against Adversarial Attack

    1 Double Backpropagation for Training Autoencoders against Adversarial Attack Chengjin Sun, Sizhe Chen, and Xiaolin Huang, Senior Member, IEEE Abstract—Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data storage and transmission, however, the current autoencoders are easily attacked, i.e., one can slightly modify an input but has totally different codes. The vulnerability is rooted the sensitivity of the autoencoders and to enhance the robustness, we propose to adopt double backpropagation (DBP) to secure autoencoder such as VAE and DRAW. We restrict the gradient from the reconstruction image to the original one so that the autoencoder is not sensitive to trivial perturbation produced by the adversarial attack. After smoothing the gradient by DBP, we further smooth the label by Gaussian Mixture Model (GMM), aiming for accurate and robust classification. We demonstrate in MNIST, CelebA, SVHN that our method leads to a robust autoencoder resistant to attack and a robust classifier able for image transition and immune to adversarial attack if combined with GMM. Index Terms—double backpropagation, autoencoder, network robustness, GMM. F 1 INTRODUCTION N the past few years, deep neural networks have been feature [9], [10], [11], [12], [13], or network structure [3], [14], I greatly developed and successfully used in a vast of fields, [15]. such as pattern recognition, intelligent robots, automatic Adversarial attack and its defense are revolving around a control, medicine [1]. Despite the great success, researchers small ∆x and a big resulting difference between f(x + ∆x) have found the vulnerability of deep neural networks to and f(x).
  • Can Temporal-Difference and Q-Learning Learn Representation? a Mean-Field Analysis

    Can Temporal-Difference and Q-Learning Learn Representation? a Mean-Field Analysis

    Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Analysis Yufeng Zhang Qi Cai Northwestern University Northwestern University Evanston, IL 60208 Evanston, IL 60208 [email protected] [email protected] Zhuoran Yang Yongxin Chen Zhaoran Wang Princeton University Georgia Institute of Technology Northwestern University Princeton, NJ 08544 Atlanta, GA 30332 Evanston, IL 60208 [email protected] [email protected] [email protected] Abstract Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks. At the core of their empirical successes is the learned feature representation, which embeds rich observations, e.g., images and texts, into the latent space that encodes semantic structures. Meanwhile, the evolution of such a feature representation is crucial to the convergence of temporal-difference and Q-learning. In particular, temporal-difference learning converges when the function approxi- mator is linear in a feature representation, which is fixed throughout learning, and possibly diverges otherwise. We aim to answer the following questions: When the function approximator is a neural network, how does the associated feature representation evolve? If it converges, does it converge to the optimal one? We prove that, utilizing an overparameterized two-layer neural network, temporal- difference and Q-learning globally minimize the mean-squared projected Bellman error at a sublinear rate. Moreover, the associated feature representation converges to the optimal one, generalizing the previous analysis of [21] in the neural tan- gent kernel regime, where the associated feature representation stabilizes at the initial one. The key to our analysis is a mean-field perspective, which connects the evolution of a finite-dimensional parameter to its limiting counterpart over an infinite-dimensional Wasserstein space.
  • Neural Network in Hardware

    Neural Network in Hardware

    UNLV Theses, Dissertations, Professional Papers, and Capstones 12-15-2019 Neural Network in Hardware Jiong Si Follow this and additional works at: https://digitalscholarship.unlv.edu/thesesdissertations Part of the Electrical and Computer Engineering Commons Repository Citation Si, Jiong, "Neural Network in Hardware" (2019). UNLV Theses, Dissertations, Professional Papers, and Capstones. 3845. http://dx.doi.org/10.34917/18608784 This Dissertation is protected by copyright and/or related rights. It has been brought to you by Digital Scholarship@UNLV with permission from the rights-holder(s). You are free to use this Dissertation in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s) directly, unless additional rights are indicated by a Creative Commons license in the record and/or on the work itself. This Dissertation has been accepted for inclusion in UNLV Theses, Dissertations, Professional Papers, and Capstones by an authorized administrator of Digital Scholarship@UNLV. For more information, please contact [email protected]. NEURAL NETWORKS IN HARDWARE By Jiong Si Bachelor of Engineering – Automation Chongqing University of Science and Technology 2008 Master of Engineering – Precision Instrument and Machinery Hefei University of Technology 2011 A dissertation submitted in partial fulfillment of the requirements for the Doctor of Philosophy – Electrical Engineering Department of Electrical and Computer Engineering Howard R. Hughes College of Engineering The Graduate College University of Nevada, Las Vegas December 2019 Copyright 2019 by Jiong Si All Rights Reserved Dissertation Approval The Graduate College The University of Nevada, Las Vegas November 6, 2019 This dissertation prepared by Jiong Si entitled Neural Networks in Hardware is approved in partial fulfillment of the requirements for the degree of Doctor of Philosophy – Electrical Engineering Department of Electrical and Computer Engineering Sarah Harris, Ph.D.
  • Population Dynamics: Variance and the Sigmoid Activation Function ⁎ André C

    Population Dynamics: Variance and the Sigmoid Activation Function ⁎ André C

    www.elsevier.com/locate/ynimg NeuroImage 42 (2008) 147–157 Technical Note Population dynamics: Variance and the sigmoid activation function ⁎ André C. Marreiros, Jean Daunizeau, Stefan J. Kiebel, and Karl J. Friston Wellcome Trust Centre for Neuroimaging, University College London, UK Received 24 January 2008; revised 8 April 2008; accepted 16 April 2008 Available online 29 April 2008 This paper demonstrates how the sigmoid activation function of (David et al., 2006a,b; Kiebel et al., 2006; Garrido et al., 2007; neural-mass models can be understood in terms of the variance or Moran et al., 2007). All these models embed key nonlinearities dispersion of neuronal states. We use this relationship to estimate the that characterise real neuronal interactions. The most prevalent probability density on hidden neuronal states, using non-invasive models are called neural-mass models and are generally for- electrophysiological (EEG) measures and dynamic casual modelling. mulated as a convolution of inputs to a neuronal ensemble or The importance of implicit variance in neuronal states for neural-mass population to produce an output. Critically, the outputs of one models of cortical dynamics is illustrated using both synthetic data and ensemble serve as input to another, after some static transforma- real EEG measurements of sensory evoked responses. © 2008 Elsevier Inc. All rights reserved. tion. Usually, the convolution operator is linear, whereas the transformation of outputs (e.g., mean depolarisation of pyramidal Keywords: Neural-mass models; Nonlinear; Modelling cells) to inputs (firing rates in presynaptic inputs) is a nonlinear sigmoidal function. This function generates the nonlinear beha- viours that are critical for modelling and understanding neuronal activity.
  • Neural Networks Shuai Li John Hopcroft Center, Shanghai Jiao Tong University

    Neural Networks Shuai Li John Hopcroft Center, Shanghai Jiao Tong University

    Lecture 6: Neural Networks Shuai Li John Hopcroft Center, Shanghai Jiao Tong University https://shuaili8.github.io https://shuaili8.github.io/Teaching/VE445/index.html 1 Outline • Perceptron • Activation functions • Multilayer perceptron networks • Training: backpropagation • Examples • Overfitting • Applications 2 Brief history of artificial neural nets • The First wave • 1943 McCulloch and Pitts proposed the McCulloch-Pitts neuron model • 1958 Rosenblatt introduced the simple single layer networks now called Perceptrons • 1969 Minsky and Papert’s book Perceptrons demonstrated the limitation of single layer perceptrons, and almost the whole field went into hibernation • The Second wave • 1986 The Back-Propagation learning algorithm for Multi-Layer Perceptrons was rediscovered and the whole field took off again • The Third wave • 2006 Deep (neural networks) Learning gains popularity • 2012 made significant break-through in many applications 3 Biological neuron structure • The neuron receives signals from their dendrites, and send its own signal to the axon terminal 4 Biological neural communication • Electrical potential across cell membrane exhibits spikes called action potentials • Spike originates in cell body, travels down axon, and causes synaptic terminals to release neurotransmitters • Chemical diffuses across synapse to dendrites of other neurons • Neurotransmitters can be excitatory or inhibitory • If net input of neuro transmitters to a neuron from other neurons is excitatory and exceeds some threshold, it fires an action potential 5 Perceptron • Inspired by the biological neuron among humans and animals, researchers build a simple model called Perceptron • It receives signals 푥푖’s, multiplies them with different weights 푤푖, and outputs the sum of the weighted signals after an activation function, step function 6 Neuron vs.
  • Unsupervised Speech Representation Learning Using Wavenet Autoencoders Jan Chorowski, Ron J

    Unsupervised Speech Representation Learning Using Wavenet Autoencoders Jan Chorowski, Ron J

    1 Unsupervised speech representation learning using WaveNet autoencoders Jan Chorowski, Ron J. Weiss, Samy Bengio, Aaron¨ van den Oord Abstract—We consider the task of unsupervised extraction speaker gender and identity, from phonetic content, properties of meaningful latent representations of speech by applying which are consistent with internal representations learned autoencoding neural networks to speech waveforms. The goal by speech recognizers [13], [14]. Such representations are is to learn a representation able to capture high level semantic content from the signal, e.g. phoneme identities, while being desired in several tasks, such as low resource automatic speech invariant to confounding low level details in the signal such as recognition (ASR), where only a small amount of labeled the underlying pitch contour or background noise. Since the training data is available. In such scenario, limited amounts learned representation is tuned to contain only phonetic content, of data may be sufficient to learn an acoustic model on the we resort to using a high capacity WaveNet decoder to infer representation discovered without supervision, but insufficient information discarded by the encoder from previous samples. Moreover, the behavior of autoencoder models depends on the to learn the acoustic model and a data representation in a fully kind of constraint that is applied to the latent representation. supervised manner [15], [16]. We compare three variants: a simple dimensionality reduction We focus on representations learned with autoencoders bottleneck, a Gaussian Variational Autoencoder (VAE), and a applied to raw waveforms and spectrogram features and discrete Vector Quantized VAE (VQ-VAE). We analyze the quality investigate the quality of learned representations on LibriSpeech of learned representations in terms of speaker independence, the ability to predict phonetic content, and the ability to accurately re- [17].
  • Approaching Hanabi with Q-Learning and Evolutionary Algorithm

    Approaching Hanabi with Q-Learning and Evolutionary Algorithm

    St. Cloud State University theRepository at St. Cloud State Culminating Projects in Computer Science and Department of Computer Science and Information Technology Information Technology 12-2020 Approaching Hanabi with Q-Learning and Evolutionary Algorithm Joseph Palmersten [email protected] Follow this and additional works at: https://repository.stcloudstate.edu/csit_etds Part of the Computer Sciences Commons Recommended Citation Palmersten, Joseph, "Approaching Hanabi with Q-Learning and Evolutionary Algorithm" (2020). Culminating Projects in Computer Science and Information Technology. 34. https://repository.stcloudstate.edu/csit_etds/34 This Starred Paper is brought to you for free and open access by the Department of Computer Science and Information Technology at theRepository at St. Cloud State. It has been accepted for inclusion in Culminating Projects in Computer Science and Information Technology by an authorized administrator of theRepository at St. Cloud State. For more information, please contact [email protected]. Approaching Hanabi with Q-Learning and Evolutionary Algorithm by Joseph A Palmersten A Starred Paper Submitted to the Graduate Faculty of St. Cloud State University In Partial Fulfillment of the Requirements for the Degree of Master of Science in Computer Science December, 2020 Starred Paper Committee: Bryant Julstrom, Chairperson Donald Hamnes Jie Meichsner 2 Abstract Hanabi is a cooperative card game with hidden information that requires cooperation and communication between the players. For a machine learning agent to be successful at the Hanabi, it will have to learn how to communicate and infer information from the communication of other players. To approach the problem of Hanabi the machine learning methods of Q- learning and Evolutionary algorithm are proposed as potential solutions.
  • Linear Prediction-Based Wavenet Speech Synthesis

    Linear Prediction-Based Wavenet Speech Synthesis

    LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis Min-Jae Hwang Frank Soong Eunwoo Song Search Solution Microsoft Naver Corporation Seongnam, South Korea Beijing, China Seongnam, South Korea [email protected] [email protected] [email protected] Xi Wang Hyeonjoo Kang Hong-Goo Kang Microsoft Yonsei University Yonsei University Beijing, China Seoul, South Korea Seoul, South Korea [email protected] [email protected] [email protected] Abstract—We propose a linear prediction (LP)-based wave- than the speech signal, the training and generation processes form generation method via WaveNet vocoding framework. A become more efficient. WaveNet-based neural vocoder has significantly improved the However, the synthesized speech is likely to be unnatural quality of parametric text-to-speech (TTS) systems. However, it is challenging to effectively train the neural vocoder when the target when the prediction errors in estimating the excitation are database contains massive amount of acoustical information propagated through the LP synthesis process. As the effect such as prosody, style or expressiveness. As a solution, the of LP synthesis is not considered in the training process, the approaches that only generate the vocal source component by synthesis output is vulnerable to the variation of LP synthesis a neural vocoder have been proposed. However, they tend to filter. generate synthetic noise because the vocal source component is independently handled without considering the entire speech To alleviate this problem, we propose an LP-WaveNet, production process; where it is inevitable to come up with a which enables to jointly train the complicated interactions mismatch between vocal source and vocal tract filter.