Deep Learning
Deep learning is a branch of machine learning that involves algorithms based on artificial neural networks for learning data representations. [1][2][3][4][5] The term “deep” in deep learning refers to the use of multiple layers in the network. Early work showed that linear perceptrons cannot serve as universal classifiers, but networks with non-polynomial activation functions and a hidden layer of infinite width can be universal classifiers.
Deep learning is a type of machine learning algorithm based on feature learning from data.Observations (such as an image) can be represented in various ways, such as a vector of pixel intensity values, or more abstractly as a series of edges or regions of specific shapes. Using certain specific representations makes it easier to learn tasks from examples (such as face recognition or facial expression recognition [6]).The advantage of deep learning is that it replaces manual feature extraction with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction.[7]
Data Mining
Data mining is an interdisciplinary branch of computer science [1][2][3]. It is a computational process that uses interdisciplinary methods from artificial intelligence, machine learning, statistics, and databases to discover patterns in relatively large datasets [1].
The overall goal of the data mining process is to extract information from a dataset and transform it into an understandable structure for further use [1].In addition to the initial analysis steps, it also involves considerations related to databases and data management, data preprocessing, modeling and inference, measures of interest, complexity considerations, as well as post-processing tasks such as structure discovery, visualization, and online updates [1].Data mining is an analytical step within “Knowledge Discovery in Databases” (KDD) [4] and essentially falls within the realm of machine learning.
Similar terms such as “data mining,” “data fishing,” and “data probing” refer to the use of data mining methods to sample portions of a larger population dataset that may be too small to reliably infer the validity of any discovered patterns through statistical inference.However, these methods can generate new hypotheses to test against larger data populations.
Machine Learning
Machine learning (abbreviated as ML) is a branch of artificial intelligence. Machine learning theory primarily focuses on designing and analyzing algorithms that enable computers to “learn” automatically.Machine learning algorithms are a class of algorithms that automatically analyze data to identify patterns and use those patterns to make predictions about unknown data. Because learning algorithms involve a great deal of statistical theory, machine learning is particularly closely linked to inferential statistics and is also referred to as statistical learning theory.In terms of algorithm design, machine learning theory focuses on feasible and effective learning algorithms (to prevent the accumulation of errors). Since many inference problems involve non-programmatic decision-making, part of machine learning research is dedicated to developing approximation algorithms that are easy to implement.
Machine learning has been widely applied in fields such as data mining, computer vision, natural language processing, biometric recognition, search engines, medical diagnosis, credit card fraud detection, securities market analysis, DNA sequencing, speech and handwriting recognition, gaming, and robotics.Over the past 30-plus years, machine learning has evolved into a multidisciplinary field that integrates various disciplines, including probability theory, statistics, approximation theory, convex analysis, computational complexity theory, and information theory.
See also: Overview of Machine Learning
Definition
Machine learning has the following definitions:
Machine learning is a branch of artificial intelligence (AI) whose primary focus is on AI, specifically on how to improve the performance of specific algorithms through empirical learning.
Machine learning is the study of computer algorithms that can automatically improve through experience.
Machine learning uses data or past experience to optimize the performance metrics of computer programs.
Additionally, computer scientist Tom Mitchell defines machine learning in his book *Machine Learning* [1] as follows:
A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance on tasks in T, as measured by P, improves with experience E.
—Tom Mitchell, *Machine Learning*
