MLAI
-
Different Machine Learning Categories and AlgorithmsMLAI 2019. 9. 30. 22:17
1. Overview At a high-level, machine learning is simply the study of teaching a computer program or algorithm how to progressively improve upon a set task that it is given. On the research side of things, machine learning can be viewed through the lens of theoretical and mathematical modeling of how this process works. However, more practically it is the study of how to build applications that e..
-
Convolutional Neural Networks(CNN)MLAI/DeepLearning 2019. 9. 30. 17:28
1. Overview In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery. CNNs are regularized versions of multilayer perceptrons. Multilayer perceptrons usually mean fully connected networks, that is, each neuron in one layer is connected to all neurons in the next layer. The "fully-connectedness" of the..
-
Difference between Deep Learning and Shallow learningMLAI/DeepLearning 2019. 9. 25. 07:27
1. Overview Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on artificial neural networks. Learning can be supervised, semi-supervised or unsupervised. Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks have been ap..
-
Term frequency–inverse document frequency(TF-IDF)MLAI/Preprocessing 2019. 9. 25. 01:34
1. Overview A document-term or term-document matrix consists of the frequency of terms that exist in a collection of documents. In the document-term matrix, rows represent documents in the collection and columns represent terms whereas the term-document matrix is the transpose of it. 1.1 Motivation we have a large number of documents: Books Academic Articles Legal Documents Websites etc A user t..