machine learning buzzwords

would sort an array. Perform an indirect sort along the given axis using the algorithm specified by the kind keyword. It returns an array of indices of the same shape as a , the index data along the given axis in sorted order. Returns an array of subscripts after a small to large order. Axis represents the dimension to compare, which defaults to the last dimension.　Some function learning in 2.pythonThe reload () function, which needs to be i

Brief introduction In recent years, because of the cloud platform, large data, high-performance computing, machine learning and other areas of progress, artificial intelligence also fire up. Face recognition, speech recognition and other related functions have been proposed, but can form products and large-scale use of small. Because it is difficult for non-professional professionals to achieve a complete s

Reference:http://www.52nlp.cn/python-%e7%bd%91%e9%a1%b5%e7%88%ac%e8%99%ab-%e6%96%87%e6%9c%ac%e5%a4%84%e7%90%86 -%e7%a7%91%e5%ad%a6%e8%ae%a1%e7%ae%97-%e6%9c%ba%e5%99%a8%e5%ad%a6%e4%b9%a0-%e6%95%b0%e6%8d%ae%e6%8c%96%e6%8e% 98A Python web crawler toolsetA real project must start with getting the data. Regardless of the text processing, machine learning and data mining, all need data, in addition to through som

steepness factor to these nonlinear functions, adjust the saturation region of the nonlinear function, adjust the shape of the training loss function, and adjust the parameter adjustment out of the saturated area.For the sigmoid function, the steepness factor (recorded as λ) can be set as follows: Δs (x) =1/(1+exp (-x/λ))2.1.4 Using numerical optimization techniquesIn order to improve the convergence speed and stability of neural network training, we can also use the numerical optimization algo

I hear that Hulu machine learning is better than a winter weekend.You can click "Machine Learning" in the menu bar to review all the previous installments of this series and comment on your thoughts and comments.At the same time, in order to make everyone better understand Hulu, the menu "about Hulu" also made the corr

sentence The main task of pattern recognition is to design a classifier that is invariant to these transformations, with the following three techniques: Structural invariance: The design of the structure has taken into account the insensitivity to the transformation, and the disadvantage is that the number of network connections becomes large Training invariance: Different sample training parameters for the same target; disadvantage: It is not guaranteed that the tr

. Optimal interval classifierThe optimal interval classifier can be regarded as the predecessor of the support vector machine, and is a learning algorithm, which chooses the specific W and b to maximize the geometrical interval. The optimal classification interval is an optimization problem such as the following:That is, select Γ,w,b to maximize gamma, while satisfying the condition: the maximum geometry in

TensorFlow learning --- getting started (1) ----- MNIST machine learning, References: http://www.tensorfly.cn/tfdoc/tutorials/mnist_beginners.html Data: http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_download.html Environment: windows + Python3.5 + tensorflow Python code From tensorflow. examples. tutorials. mnist import input_data # load train

statistical tests for each feature:false positive rate SELECTFPR, false discovery rate selectfdr, or family wise error selectfwe. The document says that if you use a sparse matrix, only the CHI2 indicator is available, and everything else must be transformed into the dense matrix. But I actually found that f_classif can also be used in sparse matrices.Recursive Feature elimination: Looping feature selectionInstead of examining the value of a variable individually, it aggregates it together for

17.1 Study of large data sets17.2 Random Gradient descent method17.3 Miniature Batch gradient descent17.4 Stochastic gradient descent convergence17.5 Online Learning17.6 mapping Simplification and data parallelism 17.1 Study of large data sets 17.2 Stochastic gradient descent method 17.3miniature Batch gradient descent 17.4 stochastic gradient descent convergence 17.5 Online learning 17.6 mapping simplification and data parallelism Ng Lesson 17th: M

This article is translated from awesome-machine-learning by bole online-toolate. Welcome to the technical translation team. For more information, see the requirements at the end of the article. This article has compiled some frameworks, libraries, and software (sorted by programming language) in the machine learning fi

How to select Super Parameters in machine learning algorithm: Learning rate, regular term coefficient, minibatch sizeThis article is part of the third chapter of "Neural networks and deep learning", which describes how to select the value of the initial hyper-parameter in the machi