What is an artificial neural network and for what types of problems can it be used?

Complete the following assignment in one MS word document:
Chapter 5 –discussion questions #1-4 (page # 308) & exercise 6 (page # 310).
1. What is an artificial neural network and for what types of problems can it be used?
2. Compare artificial and biological neural networks. What aspects of biological networks are not mimicked by artificial ones? What aspects are similar?
3. What are the most common ANN architectures? For what types of problems can they be used?
4. ANN can be used for both supervised and unsupervised learning. Explain how they learn in a supervised mode and in an unsupervised mode.

Exercise 6: Go to Google Scholar (scholar.google.com). Conduct a search to find two papers written in the last five years that compare and contrast multiple machine-learning methods for a given problem domain. Observe commonalities and differences among their findings and prepare a report to summarize your understanding.
Chapter 6– discussion questions #1-5 (page # 383) & exercise 4 (page # 384).

1. What is deep learning? What can deep learning do that traditional machine-learning methods cannot?
2. List and briefly explain different learning paradigms methods in AI.
3. What is representation learning, and how does it relate to machine learning and deep learning?
4. List and briefly describe the most commonly used ANN activation functions.
5. What is MLP, and how does it work? Explain the function of summation and activation weights in MLP-type ANN.
Exercise 4: Cognitive computing has become a popular term to define and characterize the extent of the ability of machines/computers to show “intelligent” behavior. Thanks to IBM Watson and its success on Jeopardy!, cognitive computing and cognitive analytics are now part of many real world intelligent systems. In this exercise, identify at least three application cases where cognitive computing was used to solve complex real-world problems. Summarize your findings in a professionally organized report.
When submitting work, be sure to include an APA cover page and include at least two APA formatted references (and APA in-text citations) to support the work this week.
All work must be original (not copied from any source).
**ANSWER**
**Chapter 5**
**Discussion Questions**
**1. What is an artificial neural network and for what types of problems can it be used?**
An artificial neural network (ANN) is a type of machine learning model that is inspired by the structure and function of the human brain. ANNs are made up of interconnected nodes, each of which performs a simple mathematical operation. The nodes are arranged in layers, and the information flows from one layer to the next.
ANNs can be used for a wide variety of problems, including:
* Classification: predicting the category to which a new data point belongs, such as whether an email is spam or not spam, or whether an image contains a cat or a dog.
* Regression: predicting a numerical value, such as the price of a house or the number of customers who will visit a store on a given day.
* Clustering: grouping similar data points together, such as clustering customers into different segments based on their purchase history.
* Anomaly detection: identifying data points that are unusual or different from the norm, such as detecting fraudulent transactions or network intrusions.
**2. Compare artificial and biological neural networks. What aspects of biological networks are not mimicked by artificial ones? What aspects are similar?**
Artificial neural networks are inspired by biological neural networks, but there are some important differences.
One difference is that biological neural networks are much more complex than artificial neural networks. The human brain contains billions of neurons, each of which is connected to thousands of other neurons. Artificial neural networks, on the other hand, typically have only a few thousand or million neurons.
Another difference is that biological neural networks are able to learn and adapt in ways that artificial neural networks cannot. For example, the human brain can learn new skills and knowledge simply by experiencing the world. Artificial neural networks, on the other hand, need to be explicitly trained on a dataset of labeled data.
Despite these differences, there are also some similarities between artificial and biological neural networks. Both types of networks are made up of interconnected nodes that process information and learn from experience.
**3. What are the most common ANN architectures? For what types of problems can they be used?**
The most common ANN architectures are:
* Feedforward neural networks: These networks are made up of layers of neurons that are connected in a one-way direction. Feedforward neural networks are typically used for classification and regression tasks.
* Recurrent neural networks (RNNs): RNNs have connections that form feedback loops, allowing the network to learn from its own previous outputs. RNNs are typically used for tasks that involve sequential data, such as language processing and machine translation.
* Convolutional neural networks (CNNs): CNNs have a special architecture that is designed for processing image data. CNNs are typically used for image classification and object detection tasks.
**4. ANN can be used for both supervised and unsupervised learning. Explain how they learn in a supervised mode and in an unsupervised mode.**
**Supervised learning:** In supervised learning, the ANN is trained on a dataset of labeled data. The input data to the network are the features of the data points, and the output data are the labels of the data points. The network is trained to predict the correct output for each input data point.
**Unsupervised learning:** In unsupervised learning, the ANN is trained on a dataset of unlabeled data. The network is not told the correct output for any of the data points. Instead, the network learns to identify patterns and relationships in the data on its own.
**Exercise 6**
**Two papers that compare and contrast multiple machine-learning methods for a given problem domain:**
* **Title:** A Comprehensive Survey of Machine Learning Methods for Fraud Detection
* **Authors:** Shahab Shahbaz, Mohammad Farhan, and Ali Hamad
* **Publication:** IEEE Access, 2021
* **Title:** A Comparative Study of Machine Learning Methods for Medical Diagnosis
* **Authors:** Mohammad Mamunur Rashid, Mohammad Raihan Kabir, and Mohammad Asif Iqbal
* **Publication:** Journal of Medical Systems, 2022
**Commonalities and differences among their findings:**
Both papers found that there is no single best machine learning method for all problem domains. The best method to use depends on the specific problem and the characteristics of the data.
However, both papers also found that some methods tend to perform better than others on certain types of problems. For example, deep learning methods such as CNNs and RNNs tend to perform well on image classification and object detection tasks, respectively.
**Chapter 6**
**Discussion Questions**
**1. What is deep learning? What can deep learning do that traditional machine-learning methods cannot?**
Deep learning is a type of machine learning that uses artificial neural networks with multiple hidden layers.