DOCSLIB.ORG

One Hidden Layer Neural Network Neural Networks Overview

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
One Hidden Layer Neural Network Neural Networks Overview One hidden layer Neural Network Neural Networks deeplearning.ai Overview What is a Neural Network? !" !# %& !$ x w ' = )*! + , - = .(') ℒ(-, %) b !" !# %& !$ x ["] ["] ["] ["] ["] ["] [#] [#] ["] [#] [#] [#] [#] 4 ' = 4 ! + , - = .(' ) ' = 4 - + , - = .(' ) ℒ(- , %) ,["] 4[#] ,[#] Andrew Ng One hidden layer Neural Network Neural Network deeplearning.ai Representation Neural Network Representation !" !# %& !$ Andrew Ng One hidden layer Neural Network Computing a deeplearning.ai Neural Network’s Output Neural Network Representation !" !" !# )!! + + -(') , = %& !# %& ' , !$ !$ ' = )!! + + , = -(') Andrew Ng Neural Network Representation $( $( $) #!$ + & +(!) ' = ./ $) ./ ! ' $* $* ! ! = # $ + & $( ' = +(!) $) ./ $* Andrew Ng Neural Network Representation " " " , ["] ["] " '" )" = +" ! + /" , ' " = 3()" ) !" " " " , ["] ["] " '# )# = +# ! + /# , ' # = 3()# ) ! %& # " " " , ["] ["] " '$ )$ = +$ ! + /$ , ' $ = 3()$ ) !$ " " " , ["] ["] " '( )( = +( ! + /( , ' ( = 3()( ) Andrew Ng Neural Network Representation learning ( " " Given input x: %" ( " , ! " = $ " % + ' " % ./ , " (- " " %- ( = )(! ) " (0 ! , = $ , ( " + ' , ( , = )(! , ) Andrew Ng One hidden layer Neural Network Vectorizing across deeplearning.ai multiple examples Vectorizing across multiple examples ' " = ) " ! + + " !" , " = -(' " ) %& !# ' # = ) # , " + + # ! $ , # = -(' # ) Andrew Ng Vectorizing across multiple examples for i = 1 to m: ! " ($) = ' " (($) + * " + " ($) = ,(! " $ ) ! - ($) = ' - + " ($) + * - + - ($) = ,(! - $ ) Andrew Ng One hidden layer Neural Network Explanation deeplearning.ai for vectorized implementation Justification for vectorized implementation Andrew Ng Recap of vectorizing across multiple examples for i = 1 to m !" ' " ()) = , " !()) + . " !# %& / " ()) = 0(' " ) ) !$ ' # ()) = , # / " ()) + . # / # ()) = 0(' # ) ) 1 = !(") !(#) … !(2) 6 " = , " 1 + . " 7 " = 0(6 " ) # # " # ["] 6 = , 7 + . A = /["](") ["](#) … /["](2) / 7 # = 0(6 # ) Andrew Ng One hidden layer Neural Network Activation functions deeplearning.ai Activation functions !" !# %& !$ Given x: ' " = ) " ! + + " , " = -(' " ) ' # = ) # , " + + # # # , = -(' ) Andrew Ng Pros and cons of activation functions a a x z 1 sigmoid: ! = 1 + &'( a a z z Andrew Ng One hidden layer Neural Network Why do you deeplearning.ai need non-linear activation functions? Activation function %" %. 01 %/ Given x: ! " = $ " % + ' " ( " = )["](! " ) ! . = $ . ( " + ' . ( . = )[.](! . ) Andrew Ng One hidden layer Neural Network Derivatives of deeplearning.ai activation functions Sigmoid activation function a 1 !(#) = 1 + )*+ z Andrew Ng Tanh activation function a !(#) = tanh(#) z Andrew Ng ReLU and Leaky ReLU a a z z ReLU Leaky ReLU Andrew Ng One hidden layer Neural Network Gradient descent for deeplearning.ai neural networks Gradient descent for neural networks Andrew Ng Formulas for computing derivatives Andrew Ng One hidden layer Neural Network Backpropagation deeplearning.ai intuition (Optional) Computing gradients Logistic regression % # ! = #$% + ' ) = *(!) ℒ(), /) ' Andrew Ng Neural network gradients &[$] ' )[$] &["] ![#] = &[#]' + )[#] +[#] = ,(![#]) ![0] = &[0]' + )[0] +[0] = ,(![0]) ℒ(+[0], y) )["] Andrew Ng Summary of gradient descent !'[$] = ([$] − 5 * !"[$] = !'[$]( ) !+[$] = !'[$] !'[)] = " $ ,!'[$] ∗ .[)]′(z ) ) !"[)] = !'[)]3, !+[)] = !'[)] Andrew Ng Summary of gradient descent !"[$] = '[$] − ) !6["] = 7["] − 8 , 1 , !*[$] = !"[$]' + !*["] = !6["]7 $ : 1 !-[$] = !"[$] !-["] = ;<. >?:(!6 " , '5A> = 1, BCC<!A:> = DE?C) : !"[+] = * $ .!"[$] ∗ 0[+]′(z + ) !6[$] = * " %!6["] ∗ 0[$]′(Z $ ) 1 !*[+] = !"[+]5. !*[$] = !6[$]G% : 1 !-[+] = !"[+] !-[$] = ;<. >?:(!6 $ , '5A> = 1, BCC<!A:> = DE?C) : Andrew Ng One hidden layer Neural Network Random Initialization deeplearning.ai What happens if you initialize weights to zero? [!] "# !! [$] !! %& [!] "$ !$ Andrew Ng Random initialization [!] "# !! [$] !! %& [!] "$ !$ Andrew Ng.
Load more

Recommended publications
  • Getting Started with Machine Learning
    Getting Started with Machine Learning CSC131 The Beauty & Joy of Computing Cornell College 600 First Street SW Mount Vernon, Iowa 52314 September 2018 ii Contents 1 Applications: where machine learning is helping1 1.1 Sheldon Branch............................1 1.2 Bram Dedrick.............................4 1.3 Tony Ferenzi.............................5 1.3.1 Benefits of Machine Learning................5 1.4 William Golden............................7 1.4.1 Humans: The Teachers of Technology...........7 1.5 Yuan Hong..............................9 1.6 Easton Jensen............................. 11 1.7 Rodrigo Martinez........................... 13 1.7.1 Machine Learning in Medicine............... 13 1.8 Matt Morrical............................. 15 1.9 Ella Nelson.............................. 16 1.10 Koichi Okazaki............................ 17 1.11 Jakob Orel.............................. 19 1.12 Marcellus Parks............................ 20 1.13 Lydia Sanchez............................. 22 1.14 Tiff Serra-Pichardo.......................... 24 1.15 Austin Stala.............................. 25 1.16 Nicole Trenholm........................... 26 1.17 Maddy Weaver............................ 28 1.18 Peter Weber.............................. 29 iii iv CONTENTS 2 Recommendations: How to learn more about machine learning 31 2.1 Sheldon Branch............................ 31 2.1.1 Course 1: Machine Learning................. 31 2.1.2 Course 2: Robotics: Vision Intelligence and Machine Learn- ing............................... 33 2.1.3 Course
    [Show full text]
  • Face Recognition: a Convolutional Neural-Network Approach
    98 IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 8, NO. 1, JANUARY 1997 Face Recognition: A Convolutional Neural-Network Approach Steve Lawrence, Member, IEEE, C. Lee Giles, Senior Member, IEEE, Ah Chung Tsoi, Senior Member, IEEE, and Andrew D. Back, Member, IEEE Abstract— Faces represent complex multidimensional mean- include fingerprints [4], speech [7], signature dynamics [36], ingful visual stimuli and developing a computational model for and face recognition [8]. Sales of identity verification products face recognition is difficult. We present a hybrid neural-network exceed $100 million [29]. Face recognition has the benefit of solution which compares favorably with other methods. The system combines local image sampling, a self-organizing map being a passive, nonintrusive system for verifying personal (SOM) neural network, and a convolutional neural network. identity. The techniques used in the best face recognition The SOM provides a quantization of the image samples into a systems may depend on the application of the system. We topological space where inputs that are nearby in the original can identify at least two broad categories of face recognition space are also nearby in the output space, thereby providing systems. dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides for 1) We want to find a person within a large database of partial invariance to translation, rotation, scale, and deformation. faces (e.g., in a police database). These systems typically The convolutional network extracts successively larger features return a list of the most likely people in the database in a hierarchical set of layers. We present results using the [34].
    [Show full text]
  • CNN Architectures
    Lecture 9: CNN Architectures Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9 - 1 May 2, 2017 Administrative A2 due Thu May 4 Midterm: In-class Tue May 9. Covers material through Thu May 4 lecture. Poster session: Tue June 6, 12-3pm Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9 - 2 May 2, 2017 Last time: Deep learning frameworks Paddle (Baidu) Caffe Caffe2 (UC Berkeley) (Facebook) CNTK (Microsoft) Torch PyTorch (NYU / Facebook) (Facebook) MXNet (Amazon) Developed by U Washington, CMU, MIT, Hong Kong U, etc but main framework of Theano TensorFlow choice at AWS (U Montreal) (Google) And others... Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9 - 3 May 2, 2017 Last time: Deep learning frameworks (1) Easily build big computational graphs (2) Easily compute gradients in computational graphs (3) Run it all efficiently on GPU (wrap cuDNN, cuBLAS, etc) Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9 - 4 May 2, 2017 Last time: Deep learning frameworks Modularized layers that define forward and backward pass Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9 - 5 May 2, 2017 Last time: Deep learning frameworks Define model architecture as a sequence of layers Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9 - 6 May 2, 2017 Today: CNN Architectures Case Studies - AlexNet - VGG - GoogLeNet - ResNet Also.... - NiN (Network in Network) - DenseNet - Wide ResNet - FractalNet - ResNeXT - SqueezeNet - Stochastic Depth Fei-Fei Li & Justin Johnson & Serena Yeung Lecture 9 - 7 May 2, 2017 Review: LeNet-5 [LeCun et al., 1998] Conv filters were 5x5, applied at stride 1 Subsampling (Pooling) layers were 2x2 applied at stride 2 i.e.
    [Show full text]
  • Deep Learning Architectures for Sequence Processing
    Speech and Language Processing. Daniel Jurafsky & James H. Martin. Copyright © 2021. All rights reserved. Draft of September 21, 2021. CHAPTER Deep Learning Architectures 9 for Sequence Processing Time will explain. Jane Austen, Persuasion Language is an inherently temporal phenomenon. Spoken language is a sequence of acoustic events over time, and we comprehend and produce both spoken and written language as a continuous input stream. The temporal nature of language is reflected in the metaphors we use; we talk of the flow of conversations, news feeds, and twitter streams, all of which emphasize that language is a sequence that unfolds in time. This temporal nature is reflected in some of the algorithms we use to process lan- guage. For example, the Viterbi algorithm applied to HMM part-of-speech tagging, proceeds through the input a word at a time, carrying forward information gleaned along the way. Yet other machine learning approaches, like those we’ve studied for sentiment analysis or other text classification tasks don’t have this temporal nature – they assume simultaneous access to all aspects of their input. The feedforward networks of Chapter 7 also assumed simultaneous access, al- though they also had a simple model for time. Recall that we applied feedforward networks to language modeling by having them look only at a fixed-size window of words, and then sliding this window over the input, making independent predictions along the way. Fig. 9.1, reproduced from Chapter 7, shows a neural language model with window size 3 predicting what word follows the input for all the. Subsequent words are predicted by sliding the window forward a word at a time.
    [Show full text]
  • Mlops: from Model-Centric to Data-Centric AI
    MLOps: From Model-centric to Data-centric AI Andrew Ng AI system = Code + Data (model/algorithm) Andrew Ng Inspecting steel sheets for defects Examples of defects Baseline system: 76.2% accuracy Target: 90.0% accuracy Andrew Ng Audience poll: Should the team improve the code or the data? Poll results: Andrew Ng Improving the code vs. the data Steel defect Solar Surface detection panel inspection Baseline 76.2% 75.68% 85.05% Model-centric +0% +0.04% +0.00% (76.2%) (75.72%) (85.05%) Data-centric +16.9% +3.06% +0.4% (93.1%) (78.74%) (85.45%) Andrew Ng Data is Food for AI ~1% of AI research? ~99% of AI research? 80% 20% PREP ACTION Source and prepare high quality ingredients Cook a meal Source and prepare high quality data Train a model Andrew Ng Lifecycle of an ML Project Scope Collect Train Deploy in project data model production Define project Define and Training, error Deploy, monitor collect data analysis & iterative and maintain improvement system Andrew Ng Scoping: Speech Recognition Scope Collect Train Deploy in project data model production Define project Decide to work on speech recognition for voice search Andrew Ng Collect Data: Speech Recognition Scope Collect Train Deploy in project data model production Define and collect data “Um, today’s weather” Is the data labeled consistently? “Um… today’s weather” “Today’s weather” Andrew Ng Iguana Detection Example Labeling instruction: Use bounding boxes to indicate the position of iguanas Andrew Ng Making data quality systematic: MLOps • Ask two independent labelers to label a sample of images.
    [Show full text]
  • Deep Learning I: Gradient Descent
    Roadmap Intro, model, cost Gradient descent Deep Learning I: Gradient Descent Hinrich Sch¨utze Center for Information and Language Processing, LMU Munich 2017-07-19 Sch¨utze (LMU Munich): Gradient descent 1 / 40 Roadmap Intro, model, cost Gradient descent Overview 1 Roadmap 2 Intro, model, cost 3 Gradient descent Sch¨utze (LMU Munich): Gradient descent 2 / 40 Roadmap Intro, model, cost Gradient descent Outline 1 Roadmap 2 Intro, model, cost 3 Gradient descent Sch¨utze (LMU Munich): Gradient descent 3 / 40 Roadmap Intro, model, cost Gradient descent word2vec skipgram predict, based on input word, a context word Sch¨utze (LMU Munich): Gradient descent 4 / 40 Roadmap Intro, model, cost Gradient descent word2vec skipgram predict, based on input word, a context word Sch¨utze (LMU Munich): Gradient descent 5 / 40 Roadmap Intro, model, cost Gradient descent word2vec parameter estimation: Historical development vs. presentation in this lecture Mikolov et al. (2013) introduce word2vec, estimating parameters by gradient descent. (today) Still the learning algorithm used by default and in most cases Levy and Goldberg (2014) show near-equivalence to a particular type of matrix factorization. (yesterday) Important because it links two important bodies of research: neural networks and distributional semantics Sch¨utze (LMU Munich): Gradient descent 6 / 40 Roadmap Intro, model, cost Gradient descent Gradient descent (GD) Gradient descent is a learning algorithm. Given: a hypothesis space (or model family) an objective function or cost function a training set Gradient descent (GD) finds a set of parameters, i.e., a member of the hypothesis space (or specified model) that performs well on the objective for the training set.
    [Show full text]
  • Introduction-To-Deep-Learning.Pdf
    Introduction to Deep Learning Demystifying Neural Networks Agenda Introduction to deep learning: • What is deep learning? • Speaking deep learning: network types, development frameworks and network models • Deep learning development flow • Application spaces Deep learning introduction ARTIFICIAL INTELLIGENCE Broad area which enables computers to mimic human behavior MACHINE LEARNING Usage of statistical tools enables machines to learn from experience (data) – need to be told DEEP LEARNING Learn from its own method of computing - its own brain Why is deep learning useful? Good at classification, clustering and predictive analysis What is deep learning? Deep learning is way of classifying, clustering, and predicting things by using a neural network that has been trained on vast amounts of data. Picture of deep learning demo done by TI’s vehicles road signs person background automotive driver assistance systems (ADAS) team. What is deep learning? Deep learning is way of classifying, clustering, and predicting things by using a neural network that has been trained on vast amounts of data. Machine Music Time of Flight Data Pictures/Video …any type of data Speech you want to classify, Radar cluster or predict What is deep learning? • Deep learning has its roots in neural networks. • Neural networks are sets of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. Biologocal Artificial Biological neuron neuron neuron dendrites inputs synapses weight axon output axon summation and cell body threshold dendrites synapses cell body Node = neuron Inputs Weights Summation W1 x1 & threshold W x 2 2 Output Inputs W3 Output x3 y layer = stack of ∑ ƒ(x) neurons Wn xn ∑=sum(w*x) Artificial neuron 6 What is deep learning? Deep learning creates many layers of neurons, attempting to learn structured representation of big data, layer by layer.
    [Show full text]
  • Face Recognition Using Popular Deep Net Architectures: a Brief Comparative Study
    future internet Article Face Recognition Using Popular Deep Net Architectures: A Brief Comparative Study Tony Gwyn 1,* , Kaushik Roy 1 and Mustafa Atay 2 1 Department of Computer Science, North Carolina A&T State University, Greensboro, NC 27411, USA; [email protected] 2 Department of Computer Science, Winston-Salem State University, Winston-Salem, NC 27110, USA; [email protected] * Correspondence: [email protected] Abstract: In the realm of computer security, the username/password standard is becoming increas- ingly antiquated. Usage of the same username and password across various accounts can leave a user open to potential vulnerabilities. Authentication methods of the future need to maintain the ability to provide secure access without a reduction in speed. Facial recognition technologies are quickly becoming integral parts of user security, allowing for a secondary level of user authentication. Augmenting traditional username and password security with facial biometrics has already seen impressive results; however, studying these techniques is necessary to determine how effective these methods are within various parameters. A Convolutional Neural Network (CNN) is a powerful classification approach which is often used for image identification and verification. Quite recently, CNNs have shown great promise in the area of facial image recognition. The comparative study proposed in this paper offers an in-depth analysis of several state-of-the-art deep learning based- facial recognition technologies, to determine via accuracy and other metrics which of those are most effective. In our study, VGG-16 and VGG-19 showed the highest levels of image recognition accuracy, Citation: Gwyn, T.; Roy, K.; Atay, M. as well as F1-Score.
    [Show full text]
  • Recurrent Neural Network
    Recurrent Neural Network TINGWU WANG, MACHINE LEARNING GROUP, UNIVERSITY OF TORONTO FOR CSC 2541, SPORT ANALYTICS Contents 1. Why do we need Recurrent Neural Network? 1. What Problems are Normal CNNs good at? 2. What are Sequence Tasks? 3. Ways to Deal with Sequence Labeling. 2. Math in a Vanilla Recurrent Neural Network 1. Vanilla Forward Pass 2. Vanilla Backward Pass 3. Vanilla Bidirectional Pass 4. Training of Vanilla RNN 5. Vanishing and exploding gradient problems 3. From Vanilla to LSTM 1. Definition 2. Forward Pass 3. Backward Pass 4. Miscellaneous 1. More than Language Model 2. GRU 5. Implementing RNN in Tensorflow Part One Why do we need Recurrent Neural Network? 1. What Problems are Normal CNNs good at? 2. What is Sequence Learning? 3. Ways to Deal with Sequence Labeling. 1. What Problems are CNNs normally good at? 1. Image classification as a naive example 1. Input: one image. 2. Output: the probability distribution of classes. 3. You need to provide one guess (output), and to do that you only need to look at one image (input). P(Cat|image) = 0.1 P(Panda|image) = 0.9 2. What is Sequence Learning? 1. Sequence learning is the study of machine learning algorithms designed for sequential data [1]. 2. Language model is one of the most interesting topics that use sequence labeling. 1. Language Translation 1. Understand the meaning of each word, and the relationship between words 2. Input: one sentence in German input = "Ich will stark Steuern senken" 3. Output: one sentence in English output = "I want to cut taxes bigly" (big league?) 2.
    [Show full text]
  • Neural Networks and Backpropagation
    10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Neural Networks and Backpropagation Neural Net Readings: Murphy -- Matt Gormley Bishop 5 Lecture 20 HTF 11 Mitchell 4 April 3, 2017 1 Reminders • Homework 6: Unsupervised Learning – Release: Wed, Mar. 22 – Due: Mon, Apr. 03 at 11:59pm • Homework 5 (Part II): Peer Review – Expectation: You Release: Wed, Mar. 29 should spend at most 1 – Due: Wed, Apr. 05 at 11:59pm hour on your reviews • Peer Tutoring 2 Neural Networks Outline • Logistic Regression (Recap) – Data, Model, Learning, Prediction • Neural Networks – A Recipe for Machine Learning Last Lecture – Visual Notation for Neural Networks – Example: Logistic Regression Output Surface – 2-Layer Neural Network – 3-Layer Neural Network • Neural Net Architectures – Objective Functions – Activation Functions • Backpropagation – Basic Chain Rule (of calculus) This Lecture – Chain Rule for Arbitrary Computation Graph – Backpropagation Algorithm – Module-based Automatic Differentiation (Autodiff) 3 DECISION BOUNDARY EXAMPLES 4 Example #1: Diagonal Band 5 Example #2: One Pocket 6 Example #3: Four Gaussians 7 Example #4: Two Pockets 8 Example #1: Diagonal Band 9 Example #1: Diagonal Band 10 Example #1: Diagonal Band Error in slides: “layers” should read “number of hidden units” All the neural networks in this section used 1 hidden layer. 11 Example #1: Diagonal Band 12 Example #1: Diagonal Band 13 Example #1: Diagonal Band 14 Example #1: Diagonal Band 15 Example #2: One Pocket
    [Show full text]
  • Deep Layer Aggregation
    Deep Layer Aggregation Fisher Yu Dequan Wang Evan Shelhamer Trevor Darrell UC Berkeley Abstract Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of fea- Dense Connections Feature Pyramids tures in a convolutional network, a layer in isolation is not enough: compounding and aggregating these representa- tions improves inference of what and where. Architectural + efforts are exploring many dimensions for network back- bones, designing deeper or wider architectures, but how to best aggregate layers and blocks across a network deserves Deep Layer Aggregation further attention. Although skip connections have been in- Figure 1: Deep layer aggregation unifies semantic and spa- corporated to combine layers, these connections have been tial fusion to better capture what and where. Our aggregation “shallow” themselves, and only fuse by simple, one-step op- architectures encompass and extend densely connected net- erations. We augment standard architectures with deeper works and feature pyramid networks with hierarchical and aggregation to better fuse information across layers. Our iterative skip connections that deepen the representation and deep layer aggregation structures iteratively and hierarchi- refine resolution. cally merge the feature hierarchy to make networks with better accuracy and fewer parameters. Experiments across architectures and tasks show that deep layer aggregation improves recognition and resolution compared to existing riers, different blocks or modules have been incorporated branching and merging schemes. to balance and temper these quantities, such as bottlenecks for dimensionality reduction [29, 39, 17] or residual, gated, and concatenative connections for feature and gradient prop- agation [17, 38, 19].
    [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]