INTRODUCTION TO ARTIFICIAL INTELLIGENCE & MACHINE LEARNING

Artificial intelligence can be interpreted as adding human intelligence in a machine. Artificial intelligence is not a system but a discipline that focuses on making machine smart enough to tackle the problem like the human brain does. The ability to learn, understand, imagine are the qualities that are naturally found in Humans. Developing a system that has the same or better level of these qualities artificially is termed as Artificial Intelligence.

Machine Learning is a subset of AI. That is, all machine learning counts as AI, but not all AI counts as machine learning. Machine learning refers to the system that can learn by themselves. Machine learning is the study of computer algorithms that comprises of algorithms and statistical models that allow computer programs to automatically improve through experience.

“Machine learning is the tendency of machines to learn from data analysis and achieve Artificial Intelligence.”

Machine Learning is the science of getting computers to act by feeding them data and letting them learn a few tricks on their own without being explicitly programmed. Machine learning can be further classified into three types:

1. Supervised Learning
2. Unsupervised learning
3. Reinforced Learning

Difference between Machine learning and Artificial Intelligence

AI is not a system, but it can be implemented on the system to make the system intelligent. ML is a system that can extract knowledge from datasets. AI leads to wisdom or intelligence whereas ML leads to knowledge or experience. Read more>

Supervised means to oversee or direct a certain activity and make sure it is done correctly. In this type of learning the machine learns under guidance. So, at school or teachers guided us and taught us similarly in supervised learning machines learn by feeding them label data and explicitly telling them that this is the input and this is exactly how the output must look. So, the teacher, in this case, is the training data.

• Linear Regression
• Logistic Regression
• Support Vector Machine
• Naive Bayes Classifier
•  Artificial Neural Networks, etc

Unsupervised means to act without anyone’s supervision or without anybody’s direction. Now, here the data is not labeled. There is no guide and the machine has to figure out the data set given and it has to find hidden patterns in order to make predictions about the output. An example of unsupervised learning is an adult-like you and me. We do not need a guide to help us with our daily activities. We can figure things out on our own without any supervision.

• K-means clustering
• Principal Component Analysis
• Generative Adversarial Networks, etc.

Reinforcement means to establish or encourage a pattern of behavior. It is a learning method wherein an agent learns by producing actions and discovers errors or rewards. Once the agent gets trained it gets ready to predict the new data presented to it.

Let’s say a child is born. What will he do? But after some months or years, he tries to walk. So here he basically follows the hit and trial concept because he is new to the surroundings and the only way to learn is experience. We notice baby stretching and kicking his legs and starts to roll over. Then he starts crawling.  He then tries to stand up but he fails in doing so for many attempts. Then the baby will learn to support all his weight when held in a standing position. This is what reinforcement learning is.