# 오차역전파법

둘러보기로 가기
검색하러 가기

## 노트

### 위키데이터

- ID : Q798503

### 말뭉치

- There is no shortage of papers online that attempt to explain how backpropagation works, but few that include an example with actual numbers.
^{[1]} - The backpropagation algorithm was originally introduced in the 1970s, but its importance wasn't fully appreciated until a famous 1986 paper by David Rumelhart, Geoffrey Hinton, and Ronald Williams.
^{[2]} - If you're not crazy about mathematics you may be tempted to skip the chapter, and to treat backpropagation as a black box whose details you're willing to ignore.
^{[2]} - And so backpropagation isn't just a fast algorithm for learning.
^{[2]} - I've written the rest of the book to be accessible even if you treat backpropagation as a black box.
^{[2]} - Many neural network books (Haykin, 1994; Bishop, 1995; Ripley, 1996) do not formulate backpropagation in vector-matrix terms.
^{[3]} - Hinton and Salakhutdinov (2006) noted that it has been known since the 1980s that deep autoencoders, optimized through backpropagation, could be effective for nonlinear dimensionality reduction.
^{[3]} - In this chapter we discuss a popular learning method capable of handling such large learning problems—the backpropagation algorithm.
^{[4]} - In other words, backpropagation aims to minimize the cost function by adjusting network’s weights and biases.
^{[5]} - One way to train our model is called as Backpropagation.
^{[6]} - The Backpropagation algorithm looks for the minimum value of the error function in weight space using a technique called the delta rule or gradient descent.
^{[6]} - The structure of a BP network is shown in Figure 12.4.
^{[7]} - The BP network is known from the abbreviation.
^{[7]} - The BP algorithm can be summarized by the steps below: (1) Initialize all weightings and thresholds.
^{[7]} - The project describes teaching process of multi-layer neural network employing backpropagation algorithm.
^{[8]} - Only in the middle eighties the backpropagation algorithm has been worked out.
^{[8]} - It is one kind of backpropagation network which produces a mapping of a static input for static output.
^{[9]} - Recurrent backpropagation is fed forward until a fixed value is achieved.
^{[9]} - Backpropagation is an algorithm commonly used to train neural networks.
^{[10]} - Backpropagation is simply an algorithm which performs a highly efficient search for the optimal weight values, using the gradient descent technique.
^{[10]} - We’ll explain the backpropagation process in the abstract, with very simple math.
^{[10]} - The backpropagation algorithm calculates how much the final output values, o1 and o2, are affected by each of the weights.
^{[10]} - Generalizations of backpropagation exists for other artificial neural networks (ANNs), and for functions generally.
^{[11]} - Backpropagation computes the gradient in weight space of a feedforward neural network, with respect to a loss function.
^{[11]} - In the derivation of backpropagation, other intermediate quantities are used; they are introduced as needed below.
^{[11]} - This is the reason why backpropagation requires the activation function to be differentiable.
^{[11]} - Thus, for the purposes of derivation, the backpropagation algorithm will concern itself with only one input-output pair.
^{[12]} - This equation is where backpropagation gets its name.
^{[12]} - The principle of the backpropagation approach is to model a given function by modifying internal weightings of input signals to produce an expected output signal.
^{[13]} - Technically, the backpropagation algorithm is a method for training the weights in a multilayer feed-forward neural network.
^{[13]} - Running the example prints the network after the backpropagation of error is complete.
^{[13]} - However, the main learning mechanism behind these advances – error backpropagation – appears to be at odds with neurobiology.
^{[14]} - We demonstrate the learning capabilities of the model in regression and classification tasks, and show analytically that it approximates the error backpropagation algorithm.
^{[14]} - Examining the algorithm you can see why it's called backpropagation.
^{[15]} - Backpropagation with linear neurons Suppose we replace the usual non-linear \(σ\) function with \(σ(z)=z\) throughout the network.
^{[15]} - Rewrite the backpropagation algorithm for this case.
^{[15]} - As I've described it above, the backpropagation algorithm computes the gradient of the cost function for a single training example, \(C=C_x\).
^{[15]} - What if I told you those people don’t even know what machine learning and things like backpropagation really are?
^{[16]} - Now that you’ve learnt some of the main principles of Backpropagation in Machine Learning you understand how it isn’t about having technology come to life so they can abolish the human race.
^{[16]} - Backpropagation allows us to calculate the gradient of the loss function with respect to each of the weights of the network.
^{[17]} - Backpropagation involves the calculation of the gradient proceeding backwards through the feedforward network from the last layer through to the first.
^{[17]} - The backpropagation algorithm involves first calculating the derivates at layer N, that is the last layer.
^{[17]} - Initially, the network was trained using backpropagation through all the 18 layers.
^{[17]} - Backpropagation (backward propagation) is an important mathematical tool for improving the accuracy of predictions in data mining and machine learning.
^{[18]} - Artificial neural networks use backpropagation as a learning algorithm to compute a gradient descent with respect to weights.
^{[18]} - Because backpropagation requires a known, desired output for each input value in order to calculate the loss function gradient, it is usually classified as a type of supervised machine learning.
^{[18]} - Professor Geoffrey Hinton explains backpropagation.
^{[18]} - We can define the backpropagation algorithm as an algorithm that trains some given feed-forward Neural Network for a given input pattern where the classifications are known to us.
^{[19]} - Before we deep dive into backpropagation, we should be aware about who introduced this concept and when.
^{[19]} - Today, backpropagation is doing good.
^{[19]} - Neural network training happens through backpropagation.
^{[19]} - Computing Gradients (Part 2)" we will go over the actual backpropagation and see step by step how does the math work.
^{[20]} - Backpropagation is the central mechanism by which neural networks learn.
^{[21]} - Backpropagation takes the error associated with a wrong guess by a neural network, and uses that error to adjust the neural network’s parameters in the direction of less error.
^{[21]} - Backpropagation works by approximating the non-linear relationship between the input and the output by adjusting the weight values internally.
^{[22]} - The following figure shows the topology of the Backpropagation neural network that includes and input layer, one hidden layer and an output layer.
^{[22]} - The operations of the Backpropagation neural networks can be divided into two steps: feedforward and Backpropagation.
^{[22]} - Some modifications to the Backpropagation algorithm allows the learning rate to decrease from a large value during the learning process.
^{[22]} - The backpropagation algorithm — the process of training a neural network — was a glaring one for both of us in particular.
^{[23]} - Together, we embarked on mastering backprop through some great online lectures from professors at MIT & Stanford.
^{[23]} - Today, we’ll do our best to explain backpropagation and neural networks from the beginning.
^{[23]} - The backpropagation algorithm was a major milestone in machine learning because, before it was discovered, optimization methods were extremely unsatisfactory.
^{[23]} - In the next section, I'll introduce a way to visualize the process we've just developed in addition to presenting an end-to-end method for implementing backpropagation.
^{[24]} - Note: Backpropagation is simply a method for calculating the partial derivative of the cost function with respect to all of the parameters.
^{[24]} - The first way to do backpropagation is to backpropagate through a non linear function.
^{[25]} - For the backprop algorithm, we need two sets of gradients - one with respect to the states (each module of the network) and one with respect to the weights (all the parameters in a particular module).
^{[25]} - We can again use chain rule for backprop.
^{[25]} - The proposed algorithms improve the backpropagation training in terms of both convergence rate and convergence characteristics, such as stable learning and robustness to oscillations.
^{[26]} - In algorithmic modification, the Standard BP algorithm(SBP) was modified by introducing momentum term, Quasi Newton method as a second order method, and Resillent backpropation algorithm.
^{[27]} - The proposed method shows better performance when compared to standard backpropagation algorithm (SBP) and backpropagation algorithm with momentum (SBPM).
^{[27]} - Specifically, explanation of the backpropagation algorithm was skipped.
^{[28]} - Like the majority of important aspects of Neural Networks, we can find roots of backpropagation in the 70s of the last century.
^{[28]} - One of the main tasks of backpropagation is to give us information on how quickly the error changes when weights are changed.
^{[28]} - As mentioned, there are some assumptions that we need to make regarding this function in order for backpropagation to be applicable.
^{[28]} - Refer to the figure 2.12 that illustrates the backpropagation multilayer network with layers.
^{[29]}

### 소스

- ↑ A Step by Step Backpropagation Example
- ↑
^{2.0}^{2.1}^{2.2}^{2.3}Neural networks and deep learning - ↑
^{3.0}^{3.1}Backpropagation Algorithm - an overview - ↑ The Backpropagation Algorithm
- ↑ Understanding Backpropagation Algorithm
- ↑
^{6.0}^{6.1}Training A Neural Network - ↑
^{7.0}^{7.1}^{7.2}Backpropagation Algorithm - an overview - ↑
^{8.0}^{8.1}Backpropagation - ↑
^{9.0}^{9.1}Back Propagation Neural Network: Explained With Simple Example - ↑
^{10.0}^{10.1}^{10.2}^{10.3}Backpropagation in Neural Networks: Process, Example & Code - ↑
^{11.0}^{11.1}^{11.2}^{11.3}Backpropagation - ↑
^{12.0}^{12.1}Brilliant Math & Science Wiki - ↑
^{13.0}^{13.1}^{13.2}How to Code a Neural Network with Backpropagation In Python (from scratch) - ↑
^{14.0}^{14.1}Paper - ↑
^{15.0}^{15.1}^{15.2}^{15.3}2.3: The backpropagation algorithm - ↑
^{16.0}^{16.1}The Backpropagation Algorithm Demystified - ↑
^{17.0}^{17.1}^{17.2}^{17.3}Backpropagation - ↑
^{18.0}^{18.1}^{18.2}^{18.3}What is backpropagation algorithm? - ↑
^{19.0}^{19.1}^{19.2}^{19.3}An Introduction to Backpropagation Algorithm and How it Works? - ↑ Understanding Backpropagation algorithm: Introducing the math behind neural networks (Part 1)
- ↑
^{21.0}^{21.1}A Beginner's Guide to Backpropagation in Neural Networks - ↑
^{22.0}^{22.1}^{22.2}^{22.3}Mutli-Layer Perceptron - ↑
^{23.0}^{23.1}^{23.2}^{23.3}Rohan & Lenny #1: Neural Networks & The Backpropagation Algorithm, Explained - ↑
^{24.0}^{24.1}Neural networks: training with backpropagation. - ↑
^{25.0}^{25.1}^{25.2}Introduction to Gradient Descent and Backpropagation Algorithm · Deep Learning - ↑ Improving the Convergence of the Backpropagation Algorithm Using Learning Rate Adaptation Methods
- ↑
^{27.0}^{27.1}An improved third term backpropagation algorithm – inertia expanded chebyshev orthogonal polynomial - ↑
^{28.0}^{28.1}^{28.2}^{28.3}Backpropagation Algorithm in Artificial Neural Networks - ↑ 2.4.4 Backpropagation Learning Algorithm

## 메타데이터

### 위키데이터

- ID : Q798503