coursera neural networks for machine learning

Neural network and support vector machine for deep learningIntroduction: Neural Networks (neural network) and support vector machines (SVM MACHINES,SVM) are the representative methods of statistical learning. It can be thought tha

of the "object" in the "the position with the maximum score Use a cost function this can explicitly model multiple objects present in the image. Because there may be many objects in the graph, the multi-class classification loss is not applicable. The author sees this task as multiple two classification questions, loss function and classification score as followsTrainingMuti-scale TestExperimentClassification MAP on VOC test: +3.1% compared with [56] MAP on VOC test: +7.

Mainly for the week content: large-scale machine learning, cases, summary(i) Random gradient descent methodIf there is a large-scale training set, the normal batch gradient descent method needs to calculate the sum of squares of errors across the entire training set, which is a very large computational cost if the learning method needs to iterate 20 times.First,

This semester has been to follow up on the Coursera Machina learning public class, the teacher Andrew Ng is one of the founders of Coursera, machine learning aspects of Daniel. This course is a choice for those who want to understand and master

Mainly for the sixth week Content machine learning application recommendations and system design.What to do nextWhen training good one model, predicting unknown data discovery, how to improve it? Get more examples of training Try to reduce the number of features Try to get more features Try adding two-item features Try to reduce the degree of normalization λ Try to increase the

I've been talking about why machines can learn, and starting with this lesson are some basic machine learning algorithms, i.e. how machines learn.This lesson is about linear regression, starting with the minimization of Ein, introducing the Hat Matrix to understand the geometric meaning. Finally, the linear regression and binary classification are compared, and the reason why linear regression can be used t

Mainly for the ninth week content: Anomaly detection, recommendation system(i) Anomaly detection (DENSITY estimation) kernel density estimation ( Kernel density estimation X (1) , X (2) ,.., x (m) If the data set is normal, we want to know the new data X (test) p (x) After density estimation, it is a common method to select a probability threshold to determine whether it is an anomaly, which is often used in anomaly detection. Such as: Gaussian distributionThe Gaussian k

a patient's tumour is malignant, depending on the size of the patient's tumour:Of course, sometimes we use more than one variable, such as the age of the patient, the size and shape of the tumour, and so on.In the picture, the circle represents benign and the fork is malignant, and the problem we want to learn becomes the division of benign tumors and malignant tumors.This problem is also called classification problem, the classification of the use of discrete values. We want to use this algori

This is what we have learned (except decision tree)Here is a typical decision tree algorithm, with four places to choose from:Then introduced a cart algorithm: By decision Stump divided into two categories, the criterion for measuring subtree is that the data are divided into two categories, the purity of these two types of data (purifying).The following is a measure of purity:Finally, when to stop:Decision tree may be overfitting, reducing the number of Ein and leaves (indicating the complexity

cost function least.The algorithm is:After derivation, get:Note: Although the resulting gradient descent algorithm appears to be the same as the gradient descent algorithm for linear regression, the hypothetical function here differs from the linear regression, so it is actually different. In addition, it is still necessary to perform feature scaling before applying the gradient descent algorithm.In addition, there are some alternatives to the gradient descent algorithm:In addition to the gradi

general, multiplication does not satisfy the exchange law: $ \ Matrix {A} \ times \ matrix {B} \ not = \ matrix {B} \ times \ matrix {A} $Special Matrix $ \ Matrix {I }=\ matrix {I _ {n \ times N }}=\ begin {bmatrix} 1 0 \ cdots 0 0 \ Cr0 1 \ cdots 0 0 \ Cr \ vdots \ vdots \ Cr0 0 \ cdots 1 0 \ Cr0 0 \ cdots 0 1 \ Cr \ end {bmatrix} $ For any matrix $ \ matrix {A} $: $ \ Matrix {A} \ times \ matrix {I }=\ matrix {I} \ times \ matrix {A }=\ matrix {A} $Inverse Matrix and inverte

In this section, a linear model is introduced, and several linear models are compared, and the linear regression and the logistic regression are used for classification by the conversion error function.More important is this diagram, which explains why you can use linear regression or a logistic regression to replace linear classificationThen the stochastic gradient descent method is introduced, which is an improvement to the gradient descent method, which greatly improves the efficiency.Finally

This section is about the nuclear svm,andrew Ng's handout, which is also well-spoken.The first is kernel trick, which uses nuclear techniques to simplify the calculation of low-dimensional features by mapping high-dimensional features. The handout also speaks of the determination of the kernel function, that is, what function K can use kernel trick.In addition, the kernel function can measure the similarity of two features, the greater the value, the more similar.Next is the polynomial Kernel, w

-Polynomial regressionSince linear regression does not apply to all data, sometimes we need to use curves to fit our data, for example, with two-times polynomial:Or three-time polynomial:Usually we need to look at the data before deciding what model to try to fit.After that, we can make:The two-time polynomial is then converted to a linear regression model.It is worth noting that if we adopt a polynomial regression model, feature scaling is necessary before the gradient descent algorithm is run.

the transpose of the Matrix.-Gradient descent for multiple variablesSimilar to univariate/feature linear regression, in multivariable/feature linear regression, we will also define a cost function, namely:Our goal is the same as the problem in univariate/characteristic linear regression, which is to find out the combination of parameters that make the cost function least.Therefore, the multivariable/linear regression gradient descent algorithm is:ThatAfter the derivative number can be obtained:

random values, we will find that some areas of the value effect is better, then we in this area to refine the value, more dense value.2-Select the appropriate range of hyper-parameters The previously mentioned random value is not a random uniform value within the range of valid values, but a uniform value after selecting the appropriate ruler.For the number of neurons in a layer in a neural network, we can do a uniform search within a certain range,

Welcome and Introductionoverviewreadinglog 9/9 videos and quiz completed; 10/29 Review; Note1.1 Welcome 1) What are machine learning? Machine learning are the science of getting compters to learn, without being explicitly programmed. 1.2 Introduction Linear reg

relationship scenarios. In recent years, the most popular neural network algorithm, which can deal with many problems in the field of machine learning. Neural network algorithms have the ability of linear and nonlinear learning algorithms.Neural

Wang, Min, Baoyuan Liu, and Hassan Foroosh. "Factorized convolutional neural Networks." ArXiv preprint (2016). This paper focuses on the optimization of the convolution layer in the deep network, which has three unique features:-Can be trained directly . You do not need to train the original model first, then use the sparse, compressed bits and so on to compress.-Maintain the original input and output of th

 II. Linear Regression with one Variable (Week 1)-Model representationIn the case of previous predictions of house prices, let's say that our training set of regression questions (Training set) looks like this:We use the following notation to describe the amount of regression problems:-M represents the number of instances in the training set-X represents the feature/input variable-Y represents the target variable/output variable-(x, y) represents an instance of a training set-Representing the