Page 257 - Artificial Intellegence_v2.0_Class_9
P. 257
UNIT-3
NEURAL NETWORKS
Learning Outcomes
• Why do we use Neural Networks? • Applications of Neural Networks
• Advantages of Neural Network • AI Models
• Human Nervous System • Relation between the Neural Network and Nervous System
• Working of Neural Networks • Types of Neural Networks
Neural networks form a base of deep learning, a subfield of machine learning where algorithms are inspired by
the structure of the human brain. Neural networks take input data, train themselves to recognise the patterns
in this data and then predict the output for a new set of similar data. The most impressive aspect of neural
networks is that once trained, they learn on their own just like human brain.
Why do we use Neural Networks?
Neural networks are a series of algorithms used to recognise hidden patterns in raw data, cluster and classify it,
continuously learn and improve. They are used in a variety of applications in stock markets, sales and marketing trends,
risk assessment and fraud detection. The main advantage is that the data features can be extracted automatically by
the machine without the input from the developer. Neural networks are primarily used for solving problems with large
datasets, like images. To summarize the need to use neural networks:
Large Neural Network
Model Performance Traditional Machine Learning Algorithms
Medium Neural Network
Small Neural Network
Size of Data
• It can extract data features automatically without the input from the developer.
• It is fast and efficient way to solve problems with large datasets, such as images.
• It is essentially a system of machine learning algorithms to perform certain tasks.
• The larger neural networks tend to perform better with larger amounts of data whereas the traditional machine
learning algorithm stops improving after a certain saturation point. See the figure:
Neural Networks 255

