Abstract
This chapter first provides an overview with examples of what neural networks (NN), machine learning (ML), and artificial intelligence (AI) are and their applications in biomedical and business situations. The characteristics of 29 types of neural networks are provided including their distinctive graphical illustrations. A survey of current open-source software (OSS) for neural networks, neural network software available for free trail download for limited time use, and open-source software (OSS) for machine learning (ML) are provided. Characteristics of artificial intelligence (AI) technologies for machine learning available as open source are discussed. Illustrations of applications of neural networks, machine learning, and artificial intelligence are presented as used in the daily operations of a large internationally-based software company for optimal configuration of their Helix Data Capacity system.
Top1. Introduction
1.1. Neural Networks (NN)
A Neural Network (NN) is a network consisting or arcs and nodes or circuit of neurons. An Artificial Neural Network (ANN) is composed of artificial neurons or nodes. (Wikipedia, 2021). A Neural Network (NN) can be either a biological neural network, made up of real biological neurons, or an Artificial Neural Network, for solving Artificial Intelligence (AI) problems. (Wikipedia, 2021a).
Figure 1 shows a basic Neural Network with an input layer, processing layer, and output layer of nodes. The connections of the biological neuron are modeled as weights. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed. This activity is referred to as a linear combination. An activation function controls the amplitude of the output. For example, an acceptable range of output is usually between 0 and 1, or it could be −1 and 1. (Wikipedia, 2021a)
Figure 1. Feed Forward Neural Network used for Image Classification Task with Machine Learning
The reader is referred to previous work on computer modeling of neural networks that includes comparing learning rules using computer graphics in Segall (2004, 2003, 2001, 1996, 1995), in Segall & Zhang (2006) for applications of neural networks and genetic algorithm data mining techniques in bioinformatics discovery, Fish & Segall (2002) for a visual analysis of learning rule effects and variable importance for neural networks employed in data mining operations, and Biedenbender et al. (2011) for text mining using rule based and neural network based approaches. A basic overview of neural networks for beginners is presented by Russo (2019), SAS (2020b), Taylor (2017), and Haykin (2020).
1.2. Machine Learning (ML)
Machine learning (ML) is the study of computer algorithms that improve automatically through experience, and is a subset of artificial intelligence. Machine learning algorithms build a model based on sample data, known as “training data”. (Wikipedia, 2021b)
Machine learning approaches are traditionally divided into three broad categories of (1.) supervised learning, (2.) unsupervised learning, and (3.) reinforcement learning. Supervised learning is when the computer is presented with example inputs and desired outputs. Unsupervised learning is when learning is on its own to find structure in its input such as discover hidden patterns in data, Reinforcement learning is when a computer program interacts with a dynamic environment in which it must perform a pre-specified goal. (Wikipedia, 2021b)
A basic overview of machine learning is presented in Henderson (2019). Other related research on machine learning were presented by Chouldechove and Roth (2020), David (2020), Geron (2020), G2 (2020), Hasan (2020), Haykin (2020), Jensen (2018), Jones (2018), Kelleher et al. (2015), McForckman (2020), Meng et al. (2015), Ramezani (2020), Rhys (2020), SAS (2020c), and TrustRadius (2020). One hundred and one (101) machine learning algorithms for data science with ‘cheat sheets’ was presented by Piccini (2019). Open-Source machine learning tools are discussed by Algorithmia (2019) and Springboard India (2019), Yegulalp (2020) and well as others as discussed in Table 3 of this chapter.
Key Terms in this Chapter
Multi-Factor Prediction: Used for evaluation or estimates of factors of complex systems.
Helix Capacity Optimization: BMC Helix Capacity Optimization is a capacity optimization solution that aligns Information Technology (IT) resources with business service demands, optimizing resource usage and reducing costs ( BMC, 2021 ).
Neural Networks (NN): A network or circuit of neurons, or in a modern sense, an artificial neural network, composed of artificial neurons or nodes ( Wikipedia, 2021a ).
Open-Source Software (OSS): A type of computer software in which source code is released under a license in which the copyright holder grants users the rights to use, study, change, and distribute the software to anyone and for any purpose ( Wikipedia, 2021d ).
Artificial Intelligence (AI): Intelligence demonstrated by machines, unlike the natural intelligence displayed by humans and animals, which involves consciousness and emotionality ( Wikipedia, 2021c ).
Machine Learning (ML): A part of artificial intelligence that is the study of computer algorithms that improve automatically through experience. Machine learning algorithms build a model based on sample data, known as “training data,” in order to make predictions or decisions without being explicitly programmed to do so ( Wikipedia, 2021b ).
Deep Neural Networks (DNN): Also referred to as “deep learning” are capable of learning high-level features with more complexity and abstraction than shallower neural networks (Sse et al., 2020 AU57: The in-text citation "Sse et al., 2020" is not in the reference list. Please correct the citation, add the reference to the list, or delete the citation. , pp. 3, 7).