Performance Analysis of Various Activation Functions Using LSTM Neural Network for Movie Recommendation Systems

Total Page:16

File Type:pdf, Size:1020Kb

Performance Analysis of Various Activation Functions Using LSTM Neural Network for Movie Recommendation Systems DEGREE PROJECT IN TECHNOLOGY, FIRST CYCLE, 15 CREDITS STOCKHOLM, SWEDEN 2020 Performance Analysis of Various Activation Functions Using LSTM Neural Network For Movie Recommendation Systems ANDRÉ BROGÄRD PHILIP SONG KTH ROYAL INSTITUTE OF TECHNOLOGY SCHOOL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE Performance Analysis of Various Activation Functions Using LSTM Neural Network For Movie Recommendation Systems ANDRÉ BROGÄRD, PHILIP SONG Degree Project in Computer Science, DD142X Date: June 8, 2020 Supervisor: Erik Fransén Examiner: Pawel Herman School of Electrical Engineering and Computer Science Swedish title: Prestandaanalys av olika aktiveringsfunktioner i LSTM neurala nätverk applicerat på rekommendationssystem för filmer iii Abstract The growth of importance and popularity of recommendations system has in- creased in many various areas. This thesis focuses on recommendation sys- tems for movies. Recurrent neural networks using LSTM blocks have shown some success for movie recommendation systems. Research has indicated that by changing activation functions in LSTM blocks, the performance, measured as accuracy in predictions, can be improved. In this study we compare four different activation functions (hyperbolic tangent, sigmoid, ELU and SELU activation functions) used in LSTM blocks, and how they impact the predic- tion accuracy of the neural networks. Specifically, they are applied to the block input and the block output of the LSTM blocks. Our results indicate that the hyperbolic tangent, which is the default, and sigmoid function perform about the same, whereas the ELU and SELU functions perform worse. Further re- search is needed to identify other activation functions that could improve the prediction accuracy and improve certain aspects of our methodology. iv Sammanfattning Rekommendationssystem har ökat i betydelse och popularitet i många olika områden. Denna avhandling fokuserar på rekommendationssystem för filmer. Recurrent neurala nätverk med LSTM blocks har visat viss framgång för re- kommendationssystem för filmer. Tidigare forskning har indikerat att en änd- ring av aktiverings funktioner har resulterat i förbättrad prediktering. I denna studie jämför vi fyra olika aktiveringsfunktioner (hyperbolic tangent, sigmoid, ELU and SELU) som appliceras i LSTM blocks och hur de påverkar predik- teringen i det neurala nätverket. De appliceras specifikt på block input och block output av LSTM blocken. Våra resultat indikerar att den hyperboliska tangentfunktionen, som är standardvalet, och sigmoid funktionen presterar li- ka, men ELU och SELU presterar båda sämre. Ytterligare forskning krävs för att indentifiera andra aktiveringsfunktioner och för att förbättra flera delar av metodologin. Contents 1 Introduction 1 1.1 Problem Statement . .2 1.2 Scope . .2 2 Background 3 2.1 Artifical Neural Networks . .3 2.2 Multilayer Perception ANN . .4 2.3 Recurrent Neural Network . .4 2.4 Long Short-Term Memory . .5 2.4.1 LSTM Architecture . .5 2.4.2 Activation Functions . .6 2.5 Metrics . .9 2.6 Related work . 10 3 Methods 12 3.1 Dataset . 12 3.2 Implementation . 12 3.3 Evaluation . 13 4 Results 14 5 Discussion 17 5.1 Result . 17 5.2 Improvements . 18 6 Conclusions 19 Bibliography 20 v Chapter 1 Introduction With more online movie platforms becoming available, people have a lot of movie content to choose from. According to a study from Ericsson, people spend up to one hour per day searching for movie content [1]. Seeking to min- imize this time, movie recommendation systems have been developed using Artificial Intelligence [2]. Recommendation systems aim to solve the problem of information over- loading, which denies access to interesting items, by filtering information [3]. One such way is through collaborative filtering (CF) where similar users’ in- terests are considered [3]. Popular approaches to CF include the use of neural networks, and in [4] it is demonstrated that CF can be converted to a sequence prediction problem with the use of recurrent neural networks (RNN). Long Short-Term Memory (LSTM), an RNN with LSTM blocks, was de- signed in order to solve a problem with RNN and has shown an improvement in performance [5]. LSTM has been applied in several recommendation systems [6] targeted at both entertainment (movie, music, videos) and e-commerce set- tings and has outperformed state-of-the-art models in many cases. In [4] an LSTM neural network was applied to the top-N recommendation problem, using the default choice of activation functions, recommending 10 movies the user would be interested in seeing next. The rating of a movie was ignored, only the sequence of watched movies was considered. It was observed that extra features such as age, rating or sex did not lead to an increase in accuracy. Both the Movielens and Netflix dataset were used and LSTM outperformed all baseline models in nearly all metrics. This study will use the same framework as in [4]. Since there has been success in switching activation functions [7], the study will compare different choices of activation functions in LSTM blocks and its impact on prediction 1 2 CHAPTER 1. INTRODUCTION accuracy in the context of movie recommendations. 1.1 Problem Statement The most important functionality for movie recommendation systems is the ability to predict a user’s preference of movies. Therefore, in our project we will investigate the performance, measured as accuracy in predictions for movies, of LSTM using various activation functions applied to the top-N rec- ommender problem in movie recommendation. To this end we pose a question: How does applying different activation functions to LSTM blocks affect the accuracy of predicting movies for users? 1.2 Scope The implementation of LSTM is the same as in [4] with small modifications. This study is therefore only considering this type of LSTM applied on the top N recommendation problem. In [4] they limit the amount of features to only three (user id, movie id and timestamp) and further conclude that more features such as sex or age doesn’t improve the accuracy of the models, unless they are all put together. We limit the features identically. Only the Movielens 1M dataset will be used in this study because of limited computational resources. Additionally, only the hyperbolic, sigmoid, ELU and SELU activation functions will be tested due to them showing promising results in previous work. Chapter 2 Background 2.1 Artifical Neural Networks Artificial Neural Networks (ANN) are a type of computing system inspired by the biological neural networks in human brains [8]. There are a lot of dif- ferent types of networks, all characterized with the following components: a set of nodes, in our case artificial neurons (nodes), and connections between these nodes called weights. Like the synapses in a biological brain, each con- nection between nodes can transmit a signal to other nodes. The neurons re- ceive inputs and some processing and computing occurs and then an output has been obtained which can be signaled to other neurons connected to it. The weight in each connection determines the strength of one node’s influence on another[9]. Figure 2.1 shows how an artificial neuron receives inputs, which are multiplied by weights and then the mathematical function, activation func- tion, determines the activation of the neuron. The activation functions will be more thoroughly discussed in section 2.4.2. Figure 2.1: An artificial Neuron 3 4 CHAPTER 2. BACKGROUND 2.2 Multilayer Perception ANN Multilayer perceptron (MLP) are comprised of one or more layers of neurons. The numbers of neurons in the input and output layer depends on the problem whereas the number of neurons in the hidden layers are arbitrary. The goal of MLPs is to approximate a function f ∗. For example, a classifier y = f ∗(x) maps an input x to a category y. The MLPs are also called feedforward neural networks because information flows through the function being evaluated from x, through the intermediate computations used to define f, and finally to the output y. There are no feedback connections in which outputs of the model are fed back to itself. If an MLP were to include feedback connections, they would be a recurrent neural network (RNN) [10]. 2.3 Recurrent Neural Network A weakness with MLP is that is lacks the ability to learn and efficiently store temporal dependencies [10]. A recurrent neural network is specialized for pro- cessing a sequence of values and they can scale to much longer sequences than networks without sequence-based specialization. Another advantage for RNN over MLP is the ability to share parameters across different parts of a model. For example, if we have two sentences, “I went to Nepal in 2009” and “In 2009, I went to Nepal”. Then extracting when the narrator went to Nepal using a machine learning model, the MLP model, which processes sentences of fixed length would have separate parameters for each input feature, which means it would need to learn all the rules of the language separately in each position in the sentence. Whereas, the RNN shares the same weights across several time steps. However, RNN has a problem with long-term memory, meaning it lacks the ability to connect present information to old information in order to achieve correct context [10]. For example, consider trying to predict the last word in the meaning “I grew up in France... I speak fluent French”. Latest information suggests the word to be a language. But to tell which specific lan- guage it is, context from further back in the text about France is needed. It is possible for the gap between the recent information and the information fur- ther back to become very large. As this gap grows RNNs become unable to use the past information as context for the recent information. Fortunately, Long Short-Term Memory neural network, is explicitly designed to solve long-term dependency problem [11]. CHAPTER 2. BACKGROUND 5 2.4 Long Short-Term Memory As discussed in previous section, RNN has a problem with long term mem- ory.
Recommended publications
  • 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.
    [Show full text]
  • 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.
    [Show full text]
  • 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.
    [Show full text]
  • 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.
    [Show full text]
  • 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.
    [Show full text]
  • 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.
    [Show full text]
  • Dynamic Modification of Activation Function Using the Backpropagation Algorithm in the Artificial Neural Networks
    (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 10, No. 4, 2019 Dynamic Modification of Activation Function using the Backpropagation Algorithm in the Artificial Neural Networks Marina Adriana Mercioni1, Alexandru Tiron2, Stefan Holban3 Department of Computer Science Politehnica University Timisoara, Timisoara, Romania Abstract—The paper proposes the dynamic modification of These functions represent the main activation functions, the activation function in a learning technique, more exactly being currently the most used by neural networks, representing backpropagation algorithm. The modification consists in from this reason a standard in building of an architecture of changing slope of sigmoid function for activation function Neural Network type [6,7]. according to increase or decrease the error in an epoch of learning. The study was done using the Waikato Environment for The activation functions that have been proposed along the Knowledge Analysis (WEKA) platform to complete adding this time were analyzed in the light of the applicability of the feature in Multilayer Perceptron class. This study aims the backpropagation algorithm. It has noted that a function that dynamic modification of activation function has changed to enables differentiated rate calculated by the neural network to relative gradient error, also neural networks with hidden layers be differentiated so and the error of function becomes have not used for it. differentiated [8]. Keywords—Artificial neural networks; activation function; The main purpose of activation function consists in the sigmoid function; WEKA; multilayer perceptron; instance; scalation of outputs of the neurons in neural networks and the classifier; gradient; rate metric; performance; dynamic introduction a non-linear relationship between the input and modification output of the neuron [9].
    [Show full text]
  • A Deep Reinforcement Learning Neural Network Folding Proteins
    DeepFoldit - A Deep Reinforcement Learning Neural Network Folding Proteins Dimitra Panou1, Martin Reczko2 1University of Athens, Department of Informatics and Telecommunications 2Biomedical Sciences Research Center “Alexander Fleming” ABSTRACT Despite considerable progress, ab initio protein structure prediction remains suboptimal. A crowdsourcing approach is the online puzzle video game Foldit [1], that provided several useful results that matched or even outperformed algorithmically computed solutions [2]. Using Foldit, the WeFold [3] crowd had several successful participations in the Critical Assessment of Techniques for Protein Structure Prediction. Based on the recent Foldit standalone version [4], we trained a deep reinforcement neural network called DeepFoldit to improve the score assigned to an unfolded protein, using the Q-learning method [5] with experience replay. This paper is focused on model improvement through hyperparameter tuning. We examined various implementations by examining different model architectures and changing hyperparameter values to improve the accuracy of the model. The new model’s hyper-parameters also improved its ability to generalize. Initial results, from the latest implementation, show that given a set of small unfolded training proteins, DeepFoldit learns action sequences that improve the score both on the training set and on novel test proteins. Our approach combines the intuitive user interface of Foldit with the efficiency of deep reinforcement learning. KEYWORDS: ab initio protein structure prediction, Reinforcement Learning, Deep Learning, Convolution Neural Networks, Q-learning 1. ALGORITHMIC BACKGROUND Machine learning (ML) is the study of algorithms and statistical models used by computer systems to accomplish a given task without using explicit guidelines, relying on inferences derived from patterns. ML is a field of artificial intelligence.
    [Show full text]
  • Two-Steps Implementation of Sigmoid Function for Artificial Neural Network in Field Programmable Gate Array
    VOL. 11, NO. 7, APRIL 2016 ISSN 1819-6608 ARPN Journal of Engineering and Applied Sciences ©2006-2016 Asian Research Publishing Network (ARPN). All rights reserved. www.arpnjournals.com TWO-STEPS IMPLEMENTATION OF SIGMOID FUNCTION FOR ARTIFICIAL NEURAL NETWORK IN FIELD PROGRAMMABLE GATE ARRAY Syahrulanuar Ngah1, Rohani Abu Bakar1, Abdullah Embong1 and Saifudin Razali2 1Faculty of Computer Systems and Software Engineering, Universiti Malaysia Pahang, Malaysia 2Faculty of Electrical and Electronic Engineering, Universiti Malaysia Pahang, Malaysia [email protected] ABSTRACT The complex equation of sigmoid function is one of the most difficult problems encountered for implementing the artificial neural network (ANN) into a field programmable gate array (FPGA). To overcome this problem, the combination of second order nonlinear function (SONF) and the differential lookup table (dLUT) has been proposed in this paper. By using this two-steps approach, the output accuracy achieved is ten times better than that of using only SONF and two times better than that of using conventional lookup table (LUT). Hence, this method can be used in various applications that required the implementation of the ANN into FPGA. Keywords: sigmoid function, second order nonlinear function, differential lookup table, FPGA. INTRODUCTION namely Gaussian, logarithmic, hyperbolic tangent and The Artificial neural network (ANN) has become sigmoid function has been done by T. Tan et al. They a growing research focus over the last few decades. It have found that, the optimal configuration for their controller been used broadly in many fields to solve great variety of can be achieved by using the sigmoid function [12].In this problems such as speed estimation [1], image processing paper, sigmoid function is being used as an activation [2] and pattern recognition [3].
    [Show full text]
  • Information Flows of Diverse Autoencoders
    entropy Article Information Flows of Diverse Autoencoders Sungyeop Lee 1,* and Junghyo Jo 2,3,* 1 Department of Physics and Astronomy, Seoul National University, Seoul 08826, Korea 2 Department of Physics Education and Center for Theoretical Physics and Artificial Intelligence Institute, Seoul National University, Seoul 08826, Korea 3 School of Computational Sciences, Korea Institute for Advanced Study, Seoul 02455, Korea * Correspondence: [email protected] (S.L.); [email protected] (J.J.) Abstract: Deep learning methods have had outstanding performances in various fields. A fundamen- tal query is why they are so effective. Information theory provides a potential answer by interpreting the learning process as the information transmission and compression of data. The information flows can be visualized on the information plane of the mutual information among the input, hidden, and output layers. In this study, we examine how the information flows are shaped by the network parameters, such as depth, sparsity, weight constraints, and hidden representations. Here, we adopt autoencoders as models of deep learning, because (i) they have clear guidelines for their information flows, and (ii) they have various species, such as vanilla, sparse, tied, variational, and label autoen- coders. We measured their information flows using Rényi’s matrix-based a-order entropy functional. As learning progresses, they show a typical fitting phase where the amounts of input-to-hidden and hidden-to-output mutual information both increase. In the last stage of learning, however, some autoencoders show a simplifying phase, previously called the “compression phase”, where input-to-hidden mutual information diminishes. In particular, the sparsity regularization of hidden activities amplifies the simplifying phase.
    [Show full text]
  • A Study of Activation Functions for Neural Networks Meenakshi Manavazhahan University of Arkansas, Fayetteville
    University of Arkansas, Fayetteville ScholarWorks@UARK Computer Science and Computer Engineering Computer Science and Computer Engineering Undergraduate Honors Theses 5-2017 A Study of Activation Functions for Neural Networks Meenakshi Manavazhahan University of Arkansas, Fayetteville Follow this and additional works at: http://scholarworks.uark.edu/csceuht Part of the Other Computer Engineering Commons Recommended Citation Manavazhahan, Meenakshi, "A Study of Activation Functions for Neural Networks" (2017). Computer Science and Computer Engineering Undergraduate Honors Theses. 44. http://scholarworks.uark.edu/csceuht/44 This Thesis is brought to you for free and open access by the Computer Science and Computer Engineering at ScholarWorks@UARK. It has been accepted for inclusion in Computer Science and Computer Engineering Undergraduate Honors Theses by an authorized administrator of ScholarWorks@UARK. For more information, please contact [email protected], [email protected]. A Study of Activation Functions for Neural Networks An undergraduate thesis in partial fulfillment of the honors program at University of Arkansas College of Engineering Department of Computer Science and Computer Engineering by: Meena Mana 14 March, 2017 1 Abstract: Artificial neural networks are function-approximating models that can improve themselves with experience. In order to work effectively, they rely on a nonlinearity, or activation function, to transform the values between each layer. One question that remains unanswered is, “Which non-linearity is optimal for learning with a particular dataset?” This thesis seeks to answer this question with the MNIST dataset, a popular dataset of handwritten digits, and vowel dataset, a dataset of vowel sounds. In order to answer this question effectively, it must simultaneously determine near-optimal values for several other meta-parameters, including the network topology, the optimization algorithm, and the number of training epochs necessary for the model to converge to good results.
    [Show full text]
  • Compositional Distributional Semantics with Long Short Term Memory
    Compositional Distributional Semantics with Long Short Term Memory Phong Le and Willem Zuidema Institute for Logic, Language and Computation University of Amsterdam, the Netherlands p.le,zuidema @uva.nl { } Abstract any continuous function (Cybenko, 1989) already make them an attractive choice. We are proposing an extension of the recur- In trying to answer the second question, the ad- sive neural network that makes use of a vari- vantages of approaches based on neural network ar- ant of the long short-term memory architec- ture. The extension allows information low chitectures, such as the recursive neural network in parse trees to be stored in a memory reg- (RNN) model (Socher et al., 2013b) and the con- ister (the ‘memory cell’) and used much later volutional neural network model (Kalchbrenner et higher up in the parse tree. This provides a so- al., 2014), are even clearer. Models in this paradigm lution to the vanishing gradient problem and can take advantage of general learning procedures allows the network to capture long range de- based on back-propagation, and with the rise of pendencies. Experimental results show that ‘deep learning’, of a variety of efficient algorithms our composition outperformed the traditional neural-network composition on the Stanford and tricks to further improve training. Sentiment Treebank. Since the first success of the RNN model (Socher et al., 2011b) in constituent parsing, two classes of extensions have been proposed. One class is to en- 1 Introduction hance its compositionality by using tensor product Moving from lexical to compositional semantics in (Socher et al., 2013b) or concatenating RNNs hor- vector-based semantics requires answers to two dif- izontally to make a deeper net (Irsoy and Cardie, ficult questions: (i) what is the nature of the com- 2014).
    [Show full text]