Fundamentals of Machine Learning

Abstract

Learning is a fundamental capability of neural networks. Learning rules are algorithms for finding suitable weights W and/or other network parameters. Learning of a neural network can be viewed as a nonlinear optimization problem for finding a set of network parameters that minimize the cost function for given examples. This kind of parameter estimation is also called a learning or training algorithm.Neural networks are usually trained by epoch. An epoch is a complete run when all the training examples are presented to the network and are processed using the learning algorithm only once. After learning, a neural network represents a complex relationship, and possesses the ability for generalization. To control a learning process, a criterion is defined to decide the time for terminating the process. The complexity of an algorithm is usually denoted as O(m), indicating that the order of number of floating-point operations is m.Learning methods are conventionally divided into supervised, unsupervised, and reinforcement learning; these schemes are illustrated in Fig. 2.1. x p and y p are the input and output of the pth pattern in the training set,ŷ p is the neural network output for the pth input, and E is an error function. From a statistical viewpoint, unsupervised learning learns the pdf of the training set, p(x), while supervised learning learns about the pdf of p( y|x). Supervised learning is widely used in classification, approximation, control, modeling and identification, signal processing, and optimization. Unsupervised learning schemes are mainly used for clustering, vector quantization, feature extraction, signal coding, and data analysis. Reinforcement learning is usually used in control and artificial intelligence.In logic and statistical inference, transduction is reasoning from observed, specific (training) cases to specific (test) cases. In contrast, induction is reasoning from observed training cases to general rules, which are then applied to the test cases. Machine learning falls into two broad classes: inductive learning or transductive learning. Inductive learning pursues the standard goal in machine learning, which is to accurately classify the entire input space. In contrast, transductive learning focuses

Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset

“…Artificial neural networks (ANNs) are computational tools used in the prediction of continuous variables or in classification, inspired by the functioning of neurons in the human brain [109]. W.S.…”

Approach for the Development of a Framework for the Identification of Activities of Daily Living Using Sensors in Mobile Devices

“…Machine learning methods are based on the creation and implementation of algorithms for the recognition and prediction of several situations based on the data acquired, and these methods are commonly classified in four categories [ 99 , 100 ], such as Supervised learning, Unsupervised learning, Reinforcement learning, and Semi-supervised Learning and Active Learning.…”

“…Supervised learning methods are based on the automatic adjustment of the network parameters, comparing the actual network output with the desired output previously defined in the data acquired, where the error obtained is the mean squared error (MSE) [ 100 ]. The input data involved in the supervised leaning should be labeled, in order to perform the comparisons.…”

Approach for the Development of a Framework for the Identification of Activities of Daily Living Using Mobile Devices’ Sensors

“…In subsection 2.5.2, the 328 pattern recognition methods are presented, which consists in a subset of the machine learning comparing the actual network output with the desired output previously defined in the data acquired, where the error obtained is the mean squared error (MSE) [94]. The input data involved in the supervised leaning should be labeled, in order to perform the comparisons.…”

“…provided during the execution of the algorithm by an artificial agent in order to maximize the total 352 expected reward [94]. …”