Artificial Intelligence in Computer Science Essay

ABSTRACT- An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information [1]. Artificial Neural Networks (ANN) also called neuro-computing, or parallel distributed processing (PDP), provide an alternative approach to be applied to problems where the algorithmic and symbolic approaches are not well suited. The objective of the neural network is to transform the inputs into meaningful outputs. There are many researches which show that brain store information as pattern. Some of these patterns are very complicated and allows us to recognize from different angles. This paper gives a review of the artificial neural network and analyses the techniques in terms of performance.

Understanding the way A.I. works is crucial to understanding A.I. goals. There are several traits that separate Artificial Intelligence from regular machines. One such trait is an A.I.’s ability to “think” through Neural Networks, which are networks made of simulated neurons and neuron layers designed to process and evaluate data. The simulated neurons are individual receptors designed to process and evaluate inputs. Following their evaluation, the neurons send an output to another simulated neuron in the next neuron layer. These neuron layers are layers of simulated neurons grouped by what type of input they receive and output they produce, that scales in complexity (Knight). MIT tech review senior editor Will Kight provided the example of

Machine Learning at its most basic is the practice of using algorithms to parse data, learn from it, and then make a determination or prediction about something in the world. So rather than hand-coding software routines with a specific set of instructions to accomplish a particular task, the machine is “trained” using large amounts of data and algorithms that give it the ability to learn how to perform the task [12]. Deep learning is another Machine Learning (ML) algorithm. Deep learning is essentially a set of techniques that help you to parameterize deep neural network structures, neural networks with many, many layers and parameters. Deep Learning breaks down tasks in ways that makes all kinds of machine assists seem possible, even likely. The confusion matrix, in Figure 8 shows that the accuracy of this model is (90.80) with weighted average precision (91.37) greater than recall (91.11) and F1-score (91.24). From the above results, it appears that Deep Learning classifier achieve higher accuracy, precision, recall, and F1-score.

Simulated neural systems (ANNs) utilize a cartoon of the way the human mind forms data. An ANN has numerous preparing units (neurons or hubs) working as one. They are exceedingly interconnected by connections (neural connections) with weights. The system has an information layer, a yield layer and any number of shrouded layers. A neuron is connected to all neurons in the following layer (fig.1.2). ANNs are helpful in tackling information escalated issues where the calculation or principles to take care of the issue are obscure or hard to express. The information structure and non-direct calculations of ANNs permit great fits to perplexing, multivariable information. ANNs process data in parallel and are strong to information mistakes. They

Cancer is tumor disease that involves the uncontrolled growth of abnormal cell in any part of the body without being detected. Millions of deaths are being caused by this vicious disease per year. Not only is its diagnosis risky but its classification is an equally difficult challenge. In our task we have developed a breast classification model using multilayer neural network approach to address this problem. We have analyzed our model on an open source breast cancer dataset and have obtained promising results with the best accuracy of 99.5%.

The idea of neural computing grew out of desire to capture pattern recognition capabilities of a biological brain. Neural network usually presented as system interconnected ‘’neuron’’ that can compute values from inputs by feeding

What did I learn in this class? It would be truly impossible for me to talk about one thing which I learned in this class, because I had not had any Artificial Intelligence experience or class before, so everything covered in class was a learning experience for me, to include JAVA programming language. Within this paper, I will talk about not only what I learned in class, but also what I found to be interesting and what I will probably use in the future. The topics I feel I learned the most about were Genetic Algorithms (GAs) and Neural Networks (NNs). A GA is a learning model that owes its performance to a metaphor of some of the mechanisms of evolution observed in nature (such as sexual reproduction and the principle of

One of this AI technologies tools is the Artificial Neural Networks which work much like the human brain and have the ability to learn from

Deep Learning (DL) has been shown to outperform most traditional machine learning methods in fields like computer vision, natural language processing, and bioinformatics. DL seeks to model high-level abstractions of data by constructing multiple layers with complex structures, which compose of hundreds millions of parameters to be tuned. For example, a deep learning structure for processing visual and other two-dimensional data, convolutional neural network (CNN) [1], which consists of three convolutional layers and three pooling layers, has more than 130 millions of parameters if the input has 28x28 pixels. While these large neural networks are powerful, we need high amount of training data. DL tasks need considerable data storage and memory bandwidth.

Robert Hecht-Nielsen. He defines an Artificial neural network as: "...a computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs(Anonymous 2013 ). Artificial Neural Networks imitate to some extent what Biological neural networks are capable of which is to process and sort information. (Yegnanarayana 2015).The field of ANN has been intensively studied in the past years. Artificial Neural networks, which are capable of processing a large amount of information simultaneously, address problems not by means of pre-specified algorithms but rather by “learning” from examples that are presented repeatedly. The uprise in popularity of neural networks is primarily due to their apparent ability to make decisions and draw conclusions when presented with complex, or partial information and to adapt their behavior to the nature of the training data. ANNs has a wide verity of uses in medicine including, data-classification and pattern-recognition tasks, such as the differential diagnosis of interstitial diseases, and have been shown to provide a potentially powerful classification tool .( Metz 2000)

One of this AI technologies tools is the Artificial Neural Networks which work much like the human brain and have the ability to learn from training

1. Feed-forward networks Feed-forward ANNs allow signals to travel one-direction only, from the input to the output. There is no feedback (loops) i.e. output of any layer does not affect that the same layer. Feed-forward ANNs usually straight forward the networks that connect inputs with outputs. They are widely used in the pattern recognition. There are two types of Feed-forward neural networks, Single-layer and Multi-layer Feed-forward neural network .

In the third research paper, researchers introduce an adap¬tive gain for the activation function used in back propa¬gation neural networks in order to get faster convergence and better performance in classification problems.

First, we have encountered one major problem that is how to interpret a neural network given its black box characteristics. We really wanted to try ourselves, giving interpretation of our results so that we dug into the existing literature and found out a very interesting research paper written by Garson in 1991. In « Illuminating the black box: a randomization approach for understanding variable contributions in artificial neural networks », Olden and al. describes Garson’s algorithm very concisely so that we could create a user-defined function on Python that replicates the method. The interpretation of the method is provided below. The outputs of the different algorithms in the context of our study:

SmolinskiG., MilanovaM. G. and HassanienA. E.: Studies in Computational Intelligence :Computational Intelligence in Biomedicine and Bioinformatics. ISBN-10: 354070776X | ISBN-13: 978-3540707769,Springer-Verlag(2011).