DOCSLIB.ORG

Statistical Active Learning in Multilayer Perceptrons

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Statistical Active Learning in Multilayer Perceptrons TNN A011 REV 1 Statistical Active Learning in Multilayer Perceptrons Kenji Fukumizu Brain Science Institute, RIKEN Hirosawa 2-1, Wako Saitama 351-0198 Japan Tel: +81-48-467-9664 Fax: +81-48-467-9693 E-mail: [email protected] Abstract | This pap er prop oses new metho ds of generating ory,we can derive a criterion on where are e ective input input lo cations actively in gathering training data, aiming lo cations to minimize the generalization error ([6]). at solving problems sp ecial to multilayer p erceptrons. One of the problems is that the optimum input lo cations which The main purp ose of this pap er is to solve prob- are calculated deterministically sometimes result in badly- lems related to sp ecial prop erties of multilayer networks. distributed data and cause lo cal minima in back-propagation training. Two probabilistic active learning metho ds, which One problem is that a learning rule like the error back- utilize the statistical variance of lo cations, are prop osed to propagation cannot always achieve the global minimum of solvethis problem. One is parametric active learning and the training error, while many statistical active learning or the other is multi-p oint-search active learning. Another se- exp erimental design metho ds assume its availability. We rious problem in applying active learning to multilayer p er- ceptrons is the singularityof a Fisher information matrix, see that learning with the optimal data which are calcu- whose regularity is assumed in many metho ds including the lated deterministically is trapp ed by lo cal minima more prop osed ones. A technique of pruning redundant hidden often than passive learning. To overcome this problem, units is prop osed to keep the regularityof a Fisher infor- mation matrix, which makes active learning applicable to we prop ose probabilistic metho ds, which generate an input multilayer p erceptrons. The e ectiveness of the prop osed data with deviation from the optimal lo cation. metho ds is demonstrated through computer simulations on simple arti cial problems and a real-world problem in color Another problem is caused by the singularityofaFisher conversion. information matrix. Many statistical active learning meth- Keywords | Active learning, Multilayer p erceptron, Fisher ods assume the regularity of a Fisher information ma- information matrix, Pruning. trix ([1],[4],[6]), which plays an imp ortant role in the asymptotic b ehavior of the least square error estimator I. Introduction ([7],[8],[9],[10],[11]). The Fisher information matrix of a MLP,however, can b e singular if the network has redun- HEN we train a learning machine like a feedforward dant hidden units. Since active learning metho ds usually neural network to estimate the true input-output re- W require that the prepared mo del includes the true function, lation of the target system, wemust prepare input vectors, the numb er of hidden units must b e large enough to realize observe the corresp onding output vectors, and pair them it with high accuracy. Thus, the mo del tends to b e redun- to make training data. It is well known that we can im- dant esp ecially in active learning. To solve this problem, prove the ability of a learning machine by designing the we prop ose active learning with hidden unit pruning based input of training data. Such metho ds of selecting the lo ca- on the regularity condition of a Fisher information matrix tion of input vectors have b een long studied in the name of a MLP ([12]). The metho d removes redundant hidden of experimental design ([1]), response surface methodology units to keep the regularity of a Fisher information matrix, ([2]), active learning ([3],[4]), and query construction ([5]). and makes active learning metho ds applicable to the MLP They are esp ecially imp ortant when collecting data is very mo del. exp ensive. This pap er discusses statistical active learning metho ds This pap er is organized as follows. In Section I I, we give for the multilayer p erceptron (MLP) mo del. We consider basic de nitions and terminology, and describ e an active learning of a network as statistical estimation of a regres- learning criterion. In Section I I I, we prop ose twonovel ac- sion function. The accuracy of the estimation is often eval- tive learning metho ds based on the probabilistic optimality uated using the generalization error, which is the mean of training data. In Section IV, we explain a problem con- square error b etween the true function and its estimate. In cerning the singularity of a Fisher information matrix, and this pap er, the ob jectiveofactive learning is to reduce the prop ose a pruning technique. Section V demonstrates the generalization error. Using the statistical asymptotic the- e ectiveness of the prop osed metho ds through an applica- tion to a real-world problem, and Section VI concludes this K. Fukumizu is with the Brain Science Institute, RIKEN, Saitama, Japan. E-mail: [email protected] pap er. 2 TNN A011 REV ( ) II. Active learning in statistical learning If the input vectors fx g are indep endent samples from the environmental distribution Q, such learning is called A. Basic de nitions and terminology passive. Active learning is, of course, exp ected to b e sup e- First, we give basic de nitions and terminology, which rior to passive learning with resp ect to the generalization our active learning metho ds are based on. error. When the number of training data is suciently We discuss the three-layer p erceptron mo del de ned by large, and if the true function is included in the mo del, the statistical asymptotic theory tells that E[E ] of passive ! gen H L 2 X X S , where S is the dimension learning is approximately i N f (x; )= w s u x + + ; (1 i M ) ij jk k j i of ([8],[10]). j =1 k =1 (1) B. Criterion of statistical active learning Because our principle of learning is to minimize the ex- where =(w ;::: ;w ; ;::: ; ;u ;::: ;u ; 11 MH 1 M 11 HL 1 p ectation of the generalization error, in order to construct ;::: ; ) represents weights and biases, and s(t)= 1 H t 1+e an active learning metho d we must evaluate how E[E ] gen is the sigmoidal function. dep ends on X . There are several kinds of metho ds, in N We assume that the target system which is estimated general, to estimate the generalization error. One is to use by a network is a function f (x), and the output of the the statistical asymptotic theory ([7]), and another one is system is observed with an additive Gaussian noise. Then, to use resampling techniques like b o otstrap ([13]) or cross- an output data y follows validation ([14]). The concept of structural risk minimiza- tion (SRM, [15]) develop ed by Vapnik also gives a solid y = f (x)+Z ; (2) basis to discuss generalization problems. In this pap er, we where Z is a random vector with a zero mean and a scalar employ a metho d based on the asymptotic theory. The 2 covariance I . To obtain a set of training data D = resampling techniques, which estimate the generalization M ( ) ( ) f(x ; y ) j = 1;:::;Ng, we prepare input vectors error using given training data, is not suitable for active ( ) X = fx g, feed them to the target system, and observe learning in whichwehavetoknowhow the generalization N ( ) output vectors fy g sub ject to eq.(2). The problem of error dep ends on an input p oint b efore the data is actually active learning is how to prepare X . generated. We do not adopt the SRM principle either, b e- N When a set of training data D is given, we employ the cause it is based on the b ound of the worst case unlike our ^ ob jective to minimize the exp ectation of the generalization least square error (LSE) estimator ,thatis, error. N X For the approximation of eq.(4), we assume that the ( ) ( ) 2 ^ = arg min ky f (x ; )k : (3) true function f (x) is completely included in the mo del and =1 f (x; )=f (x). This assumption is not rigorously satis- 0 ed in practical problems. In general, the exp ectation of Unlike linear mo dels whose exp erimental design has b een the generalization error can b e decomp osed as extensively studied in the eld of statistics ([1]), the solu- Z tion of eq.(3) cannot be rigorously calculated in the case 2 ^ E[E ] = E kf (x; ) f (x; )k dQ(x) of neural networks. An iterative learning rule like the er- gen o ror back-propagation is needed to obtain an approximation Z ^ 2 of . To derive an active learning criterion, however, we + kf (x; ) f (x)k dQ(x); (5) o ^ assume the availability of . A problem related to this R assumption is discussed later. where is the parameter that gives min kf (x; ) o o We use the generalization error to evaluate the ability 2 f (x)k dQ(x). The rst and the second terms in eq.(5) are of a trained network. For the de nition, weintro duce the called the variance and the bias of the mo del resp ectively. environmental probability Q, whichgives indep endent input Mo o dy ([16]), for example, discusses the generalization er- vectors in the actual environment where a trained network ror in the framework of nonparametric regression which should b e lo cated. In system identi cation, for example, Q allows the mo del bias.
Load more

Recommended publications
  • Malware Classification with BERT
    San Jose State University SJSU ScholarWorks Master's Projects Master's Theses and Graduate Research Spring 5-25-2021 Malware Classification with BERT Joel Lawrence Alvares Follow this and additional works at: https://scholarworks.sjsu.edu/etd_projects Part of the Artificial Intelligence and Robotics Commons, and the Information Security Commons Malware Classification with Word Embeddings Generated by BERT and Word2Vec Malware Classification with BERT Presented to Department of Computer Science San José State University In Partial Fulfillment of the Requirements for the Degree By Joel Alvares May 2021 Malware Classification with Word Embeddings Generated by BERT and Word2Vec The Designated Project Committee Approves the Project Titled Malware Classification with BERT by Joel Lawrence Alvares APPROVED FOR THE DEPARTMENT OF COMPUTER SCIENCE San Jose State University May 2021 Prof. Fabio Di Troia Department of Computer Science Prof. William Andreopoulos Department of Computer Science Prof. Katerina Potika Department of Computer Science 1 Malware Classification with Word Embeddings Generated by BERT and Word2Vec ABSTRACT Malware Classification is used to distinguish unique types of malware from each other. This project aims to carry out malware classification using word embeddings which are used in Natural Language Processing (NLP) to identify and evaluate the relationship between words of a sentence. Word embeddings generated by BERT and Word2Vec for malware samples to carry out multi-class classification. BERT is a transformer based pre- trained natural language processing (NLP) model which can be used for a wide range of tasks such as question answering, paraphrase generation and next sentence prediction. However, the attention mechanism of a pre-trained BERT model can also be used in malware classification by capturing information about relation between each opcode and every other opcode belonging to a malware family.
    [Show full text]
  • Fun with Hyperplanes: Perceptrons, Svms, and Friends
    Perceptrons, SVMs, and Friends: Some Discriminative Models for Classification Parallel to AIMA 18.1, 18.2, 18.6.3, 18.9 The Automatic Classification Problem Assign object/event or sequence of objects/events to one of a given finite set of categories. • Fraud detection for credit card transactions, telephone calls, etc. • Worm detection in network packets • Spam filtering in email • Recommending articles, books, movies, music • Medical diagnosis • Speech recognition • OCR of handwritten letters • Recognition of specific astronomical images • Recognition of specific DNA sequences • Financial investment Machine Learning methods provide one set of approaches to this problem CIS 391 - Intro to AI 2 Universal Machine Learning Diagram Feature Things to Magic Vector Classification be Classifier Represent- Decision classified Box ation CIS 391 - Intro to AI 3 Example: handwritten digit recognition Machine learning algorithms that Automatically cluster these images Use a training set of labeled images to learn to classify new images Discover how to account for variability in writing style CIS 391 - Intro to AI 4 A machine learning algorithm development pipeline: minimization Problem statement Given training vectors x1,…,xN and targets t1,…,tN, find… Mathematical description of a cost function Mathematical description of how to minimize/maximize the cost function Implementation r(i,k) = s(i,k) – maxj{s(i,j)+a(i,j)} … CIS 391 - Intro to AI 5 Universal Machine Learning Diagram Today: Perceptron, SVM and Friends Feature Things to Magic Vector
    [Show full text]
  • Introduction to Machine Learning
    Introduction to Machine Learning Perceptron Barnabás Póczos Contents History of Artificial Neural Networks Definitions: Perceptron, Multi-Layer Perceptron Perceptron algorithm 2 Short History of Artificial Neural Networks 3 Short History Progression (1943-1960) • First mathematical model of neurons ▪ Pitts & McCulloch (1943) • Beginning of artificial neural networks • Perceptron, Rosenblatt (1958) ▪ A single neuron for classification ▪ Perceptron learning rule ▪ Perceptron convergence theorem Degression (1960-1980) • Perceptron can’t even learn the XOR function • We don’t know how to train MLP • 1963 Backpropagation… but not much attention… Bryson, A.E.; W.F. Denham; S.E. Dreyfus. Optimal programming problems with inequality constraints. I: Necessary conditions for extremal solutions. AIAA J. 1, 11 (1963) 2544-2550 4 Short History Progression (1980-) • 1986 Backpropagation reinvented: ▪ Rumelhart, Hinton, Williams: Learning representations by back-propagating errors. Nature, 323, 533—536, 1986 • Successful applications: ▪ Character recognition, autonomous cars,… • Open questions: Overfitting? Network structure? Neuron number? Layer number? Bad local minimum points? When to stop training? • Hopfield nets (1982), Boltzmann machines,… 5 Short History Degression (1993-) • SVM: Vapnik and his co-workers developed the Support Vector Machine (1993). It is a shallow architecture. • SVM and Graphical models almost kill the ANN research. • Training deeper networks consistently yields poor results. • Exception: deep convolutional neural networks, Yann LeCun 1998. (discriminative model) 6 Short History Progression (2006-) Deep Belief Networks (DBN) • Hinton, G. E, Osindero, S., and Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18:1527-1554. • Generative graphical model • Based on restrictive Boltzmann machines • Can be trained efficiently Deep Autoencoder based networks Bengio, Y., Lamblin, P., Popovici, P., Larochelle, H.
    [Show full text]
  • Audio Event Classification Using Deep Learning in an End-To-End Approach
    Audio Event Classification using Deep Learning in an End-to-End Approach Master thesis Jose Luis Diez Antich Aalborg University Copenhagen A. C. Meyers Vænge 15 2450 Copenhagen SV Denmark Title: Abstract: Audio Event Classification using Deep Learning in an End-to-End Approach The goal of the master thesis is to study the task of Sound Event Classification Participant(s): using Deep Neural Networks in an end- Jose Luis Diez Antich to-end approach. Sound Event Classifi- cation it is a multi-label classification problem of sound sources originated Supervisor(s): from everyday environments. An auto- Hendrik Purwins matic system for it would many applica- tions, for example, it could help users of hearing devices to understand their sur- Page Numbers: 38 roundings or enhance robot navigation systems. The end-to-end approach con- Date of Completion: sists in systems that learn directly from June 16, 2017 data, not from features, and it has been recently applied to audio and its results are remarkable. Even though the re- sults do not show an improvement over standard approaches, the contribution of this thesis is an exploration of deep learning architectures which can be use- ful to understand how networks process audio. The content of this report is freely available, but publication (with reference) may only be pursued due to agreement with the author. Contents 1 Introduction1 1.1 Scope of this work.............................2 2 Deep Learning3 2.1 Overview..................................3 2.2 Multilayer Perceptron...........................4
    [Show full text]
  • 4 Perceptron Learning
    4 Perceptron Learning 4.1 Learning algorithms for neural networks In the two preceding chapters we discussed two closely related models, McCulloch–Pitts units and perceptrons, but the question of how to find the parameters adequate for a given task was left open. If two sets of points have to be separated linearly with a perceptron, adequate weights for the comput- ing unit must be found. The operators that we used in the preceding chapter, for example for edge detection, used hand customized weights. Now we would like to find those parameters automatically. The perceptron learning algorithm deals with this problem. A learning algorithm is an adaptive method by which a network of com- puting units self-organizes to implement the desired behavior. This is done in some learning algorithms by presenting some examples of the desired input- output mapping to the network. A correction step is executed iteratively until the network learns to produce the desired response. The learning algorithm is a closed loop of presentation of examples and of corrections to the network parameters, as shown in Figure 4.1. network test input-output compute the examples error fix network parameters Fig. 4.1. Learning process in a parametric system R. Rojas: Neural Networks, Springer-Verlag, Berlin, 1996 78 4 Perceptron Learning In some simple cases the weights for the computing units can be found through a sequential test of stochastically generated numerical combinations. However, such algorithms which look blindly for a solution do not qualify as “learning”. A learning algorithm must adapt the network parameters accord- ing to previous experience until a solution is found, if it exists.
    [Show full text]
  • Perceptrons.Pdf
    Machine Learning: Perceptrons Prof. Dr. Martin Riedmiller Albert-Ludwigs-University Freiburg AG Maschinelles Lernen Machine Learning: Perceptrons – p.1/24 Neural Networks ◮ The human brain has approximately 1011 neurons − ◮ Switching time 0.001s (computer ≈ 10 10s) ◮ Connections per neuron: 104 − 105 ◮ 0.1s for face recognition ◮ I.e. at most 100 computation steps ◮ parallelism ◮ additionally: robustness, distributedness ◮ ML aspects: use biology as an inspiration for artificial neural models and algorithms; do not try to explain biology: technically imitate and exploit capabilities Machine Learning: Perceptrons – p.2/24 Biological Neurons ◮ Dentrites input information to the cell ◮ Neuron fires (has action potential) if a certain threshold for the voltage is exceeded ◮ Output of information by axon ◮ The axon is connected to dentrites of other cells via synapses ◮ Learning corresponds to adaptation of the efficiency of synapse, of the synaptical weight dendrites SYNAPSES AXON soma Machine Learning: Perceptrons – p.3/24 Historical ups and downs 1942 artificial neurons (McCulloch/Pitts) 1949 Hebbian learning (Hebb) 1950 1960 1970 1980 1990 2000 1958 Rosenblatt perceptron (Rosenblatt) 1960 Adaline/MAdaline (Widrow/Hoff) 1960 Lernmatrix (Steinbuch) 1969 “perceptrons” (Minsky/Papert) 1970 evolutionary algorithms (Rechenberg) 1972 self-organizing maps (Kohonen) 1982 Hopfield networks (Hopfield) 1986 Backpropagation (orig. 1974) 1992 Bayes inference computational learning theory support vector machines Boosting Machine Learning: Perceptrons – p.4/24
    [Show full text]
  • The Architecture of a Multilayer Perceptron for Actor-Critic Algorithm with Energy-Based Policy Naoto Yoshida
    The Architecture of a Multilayer Perceptron for Actor-Critic Algorithm with Energy-based Policy Naoto Yoshida To cite this version: Naoto Yoshida. The Architecture of a Multilayer Perceptron for Actor-Critic Algorithm with Energy- based Policy. 2015. hal-01138709v2 HAL Id: hal-01138709 https://hal.archives-ouvertes.fr/hal-01138709v2 Preprint submitted on 19 Oct 2015 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. The Architecture of a Multilayer Perceptron for Actor-Critic Algorithm with Energy-based Policy Naoto Yoshida School of Biomedical Engineering Tohoku University Sendai, Aramaki Aza Aoba 6-6-01 Email: [email protected] Abstract—Learning and acting in a high dimensional state- when the actions are represented by binary vector actions action space are one of the central problems in the reinforcement [4][5][6][7][8]. Energy-based RL algorithms represent a policy learning (RL) communities. The recent development of model- based on energy-based models [9]. In this approach the prob- free reinforcement learning algorithms based on an energy- based model have been shown to be effective in such domains. ability of the state-action pair is represented by the Boltzmann However, since the previous algorithms used neural networks distribution and the energy function, and the policy is a with stochastic hidden units, these algorithms required Monte conditional probability given the current state of the agent.
    [Show full text]
  • Perceptrons and Neural Networks
    Perceptrons and Neural Networks Manuela Veloso 15-381 - Fall 2001 15-381 – Fall 2001 Veloso, Carnegie Mellon Motivation Beginnings of AI – chess, theorem-proving,... tasks thought to require “intelligence.” Perception (language and vision) and common sense reasoning not thought to be difficult to have a machine do it. The human brain as a model of how to build intelligent machines. Brain-like machanisms - since McCulloch early 40s. Connectionism – building upon the architectures of the brain. 15-381 – Fall 2001 Veloso, Carnegie Mellon Massively parallel simple neuron-like processing elements. “Representation” – weighted connections between the elements. Learning of representation – change of weights. Common sense – extremely well organized gigantic memory of facts – indices are relevant, highly operational knowledge, access by content. Classification tasks. 15-381 – Fall 2001 Veloso, Carnegie Mellon How the Brain Works Axonal arborization Axon from another cell Synapse Dendrite Axon Nucleus Synapses Cell body or Soma 15-381 – Fall 2001 Veloso, Carnegie Mellon Memory ¢¡¤£¥£ ¦¡§£©¨ neurons, connections 15-381 – Fall 2001 Veloso, Carnegie Mellon Main Processing Unit a = g(in ) a i i j Wj,i g in Input i Output ai Links Σ Links Input Activation Output Function Function § § ¢¡¤£ ¥¤¦ § ¡© ¨ 15-381 – Fall 2001 Veloso, Carnegie Mellon Different Threshold Functions a ai i ai +1 +1 +1 t ini ini ini −1 (a) Step function (b) Sign function (c) Sigmoid function 15-381 – Fall 2001 Veloso, Carnegie Mellon Learning Networks How to acquire the right values for the connections to have the right knowledge in a network? Answer – learning: show the patterns, let the network converge the values of the connections for which those patterns correspond to stable states according to parallel relaxation.
    [Show full text]
  • Accent Transfer with Discrete Representation Learning and Latent Space Disentanglement
    Accent Transfer with Discrete Representation Learning and Latent Space Disentanglement Renee Li Paul Mure Dept. of Computer Science Dept. of Computer Science Stanford University Stanford University [email protected] [email protected] Abstract The task of accent transfer has recently become a field actively under research. In fact, several companies were established with the goal of tackling this challenging problem. We designed and implemented a model using WaveNet and a multitask learner to transfer accents within a paragraph of English speech. In contrast to the actual WaveNet, our architecture made several adaptations to compensate for the fact that WaveNet does not work well for drastic dimensionality reduction due to the use of residual and skip connections, and we added a multitask learner in order to learn the style of the accent. 1 Introduction In this paper, we explored the task of accent transfer in English speech. This is an interesting problem because it shows the ability of neural network to generate novel contents based on partial information, and this problem has not been explored as much as some of the other topics in style transfer. We believe that this task is very interesting and challenging because we will be developing the state-of-the-art model for our specific task: while there are some published papers about accent classification, so far, we have not been able to find a good pre-trained model to use for evaluating our results. Moreover, raw audio generative models are also a very active field of research, so there is not much literature or implementations for relevant tasks.
    [Show full text]
  • Perceptron 1 History of Artificial Neural Networks
    Introduction to Machine Learning (Lecture Notes) Perceptron Lecturer: Barnabas Poczos Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal publications. They may be distributed outside this class only with the permission of the Instructor. 1 History of Artificial Neural Networks The history of artificial neural networks is like a roller-coaster ride. There were times when it was popular(up), and there were times when it wasn't. We are now in one of its very big time. • Progression (1943-1960) { First Mathematical model of neurons ∗ Pitts & McCulloch (1943) [MP43] { Beginning of artificial neural networks { Perceptron, Rosenblatt (1958) [R58] ∗ A single neuron for classification ∗ Perceptron learning rule ∗ Perceptron convergence theorem [N62] • Degression (1960-1980) { Perceptron can't even learn the XOR function [MP69] { We don't know how to train MLP { 1963 Backpropagation (Bryson et al.) ∗ But not much attention • Progression (1980-) { 1986 Backpropagation reinvented: ∗ Learning representations by back-propagation errors. Rumilhart et al. Nature [RHW88] { Successful applications in ∗ Character recognition, autonomous cars, ..., etc. { But there were still some open questions in ∗ Overfitting? Network structure? Neuron number? Layer number? Bad local minimum points? When to stop training? { Hopfield nets (1982) [H82], Boltzmann machines [AHS85], ..., etc. • Degression (1993-) 1 2 Perceptron: Barnabas Poczos { SVM: Support Vector Machine is developed by Vapnik et al.. [CV95] However, SVM is a shallow architecture. { Graphical models are becoming more and more popular { Great success of SVM and graphical models almost kills the ANN (Artificial Neural Network) research. { Training deeper networks consistently yields poor results. { However, Yann LeCun (1998) developed deep convolutional neural networks (a discriminative model).
    [Show full text]
  • Chapter 10: Artificial Neural Networks
    Chapter 10: Artificial Neural Networks Dr. Xudong Liu Assistant Professor School of Computing University of North Florida Monday, 9/30/2019 1 / 17 Overview 1 Artificial neuron: linear threshold unit (LTU) 2 Perceptron 3 Multi-Layer Perceptron (MLP), Deep Neural Networks (DNN) 4 Learning ANN's: Error Backpropagation Overview 2 / 17 Differential Calculus In this course, I shall stick to Leibniz's notation. The derivative of a function at an input point, when it exists, is the slope of the tangent line to the graph of the function. 2 0 dy Let y = f (x) = x + 2x + 1. Then, f (x) = dx = 2x + 2. A partial derivative of a function of several variables is its derivative with respect to one of those variables, with the others held constant. 2 2 @z Let z = f (x; y) = x + xy + y . Then, @x = 2x + y. The chain rule is a formula for computing the derivative of the composition of two or more functions. dz dz dy 0 0 Let z = f (y) and y = g(x). Then, dx = dy · dx = f (y) · g (x). 1 Nice thing about the sigmoid function f (x) = 1+e−x : f 0(x) = f (x) · (1 − f (x)). Some Preliminaries 3 / 17 Artificial Neuron Artificial neuron, also called linear threshold unit (LTU), by McCulloch and Pitts, 1943: with one or more numeric inputs, it produces a weighted sum of them, applies an activation function, and outputs the result. Common activation functions: step function and sigmoid function. Artificial Neuron 4 / 17 Linear Threshold Unit (LTU) Below is an LTU with the activation function being the step function.
    [Show full text]
  • Multilayer Perceptron
    Advanced Introduction to Machine Learning, CMU-10715 Perceptron, Multilayer Perceptron Barnabás Póczos, Sept 17 Contents History of Artificial Neural Networks Definitions: Perceptron, MLP Representation questions Perceptron algorithm Backpropagation algorithm 2 Short History Progression (1943-1960) • First mathematical model of neurons . Pitts & McCulloch (1943) • Beginning of artificial neural networks • Perceptron, Rosenblatt (1958) . A single layer neuron for classification . Perceptron learning rule . Perceptron convergence theorem Degression (1960-1980) • Perceptron can’t even learn the XOR function • We don’t know how to train MLP • 1969 Backpropagation… but not much attention… 3 Short History Progression (1980-) • 1986 Backpropagation reinvented: . Rumelhart, Hinton, Williams: Learning representations by back-propagating errors. Nature, 323, 533—536, 1986 • Successful applications: . Character recognition, autonomous cars,… • Open questions: Overfitting? Network structure? Neuron number? Layer number? Bad local minimum points? When to stop training? • Hopfield nets (1982), Boltzmann machines,… 4 Short History Degression (1993-) • SVM: Vapnik and his co-workers developed the Support Vector Machine (1993). It is a shallow architecture. • SVM almost kills the ANN research. • Training deeper networks consistently yields poor results. • Exception: deep convolutional neural networks, Yann LeCun 1998. (discriminative model) 5 Short History Progression (2006-) Deep Belief Networks (DBN) • Hinton, G. E, Osindero, S., and Teh, Y.
    [Show full text]