Supervised, Un-Supervised, Semi-Supervised machine and Reinforcement Learning algorithms

Congratulation!!! Now you know what Artificial Intelligence and Machines Learning is. Now we can go little deeper and learn about different Machine Learning algorithms.

The most important question which comes to a beginner mind is “which algorithm should I use?” The answer to the question varies depending on many factors, including: The size, quality, and nature of data; The available computational time; The urgency of the task; and What you want to do with the data. Even an experienced data scientist cannot tell which algorithm will perform the best before trying different algorithms.

Before going into the algorithms, first we will see what Supervised, Un-Supervised, Semi-Supervised machine and Reinforcement Learning algorithms are.

What is Supervised Machine Learning?

-          In Supervised Machine learning, the Machine is given a set of data which already knows how the output should look and have an idea about the relation between the input and out. Supervised learning problems are also categorized as “regression” and “classification” problems. In regression problems machine predict a numeric or continuous variable output where as in classification problems the predicted output is discrete.  For example, if the machine is given a dataset of house prices with respect to house size, it can predict an unknown house price. Whereas if some image are labelled as dogs and cats, the machine can learn the relation between them and classify and separate some image as dog or cat. Below image may give you a better understanding-

What is Un-Supervised Machine Learning?

-          Un-Supervised allows the machine to approach a problem with minimum or no idea about how the output will look like. It can drive structures and relations from the given dataset and can find hidden patterns or grouping information from the data. It is mainly used for clustering, dimensionality reduction, feature learning, density estimation, etc. Example- KMean Clustering.

What is Semi-Supervised Machine Learning?

-          Semi-supervised machine learning algorithms fall somewhere in between supervised and unsupervised learning, since they use both labeled and unlabeled data for training – typically a small amount of labeled data and a large amount of unlabeled data. The systems that use this method are able to considerably improve learning accuracy. Usually, semi-supervised learning is chosen when the acquired labeled data requires skilled and relevant resources in order to train it / learn from it. Otherwise, acquiring unlabeled data generally doesn’t require additional resources. Example: speech recognition.

What is Reinforcement Learning?

-          Reinforcement learning algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards. Trial and error search and delayed reward are the most relevant characteristics of reinforcement learning. This method allows machines and software agents to automatically determine the ideal behaviour within a specific context in order to maximize its performance. It is employed by various software and machines to find the best possible behaviour or path it should take in a specific situation.

Okay, all set, we are now ready to learn the most popular machine learning algorithms, stay tuned for that. Please comment below for any suggestion and feedback.

Next post 10 Most Commonly Used Machine Learning Algorithms

Basic Concepts of Artificial Intelligence, Machine Learning, Deep Learning

Today we will start our journey to the world of Artificial Intelligence(AI). We will learn the basic definition of Artificial Intelligence (AI), Machine Learning(ML), Deep Learning(DL), Natural Language Processing(NLP), Computer Vision and Image Processing. Later we will go deeper with the machine learning algorithms and how those algorithm works. This tutorial is for beginners, if you have an idea of AI skip this course and go to the next lesson where I will discuss different Machine Learning algorithms.

What is Artificial Intelligence(AI)?

-          Artificial intelligence (AI) is the ability of a machine or a computer program to think and learn by doing certain task. The concept of AI is based on the idea of building machines capable of thinking, acting, and learning like humans. On other words the creating the machine capable of understanding the environment, understanding the problem and act intelligently according to the situation.

What is Machine Learning(ML)?

-          Machine Learning(ML) is an application of AI that provides system the ability to automatically learn and improve performance without being explicitly programmed. ML focuses on the development of computer program that can access data and learn for themselves. The main aim is to allow computer learn automatically without human intervention or assistance and act accordingly.

-          Next question in your mind may have, how the machine is learning? –  The answer is as human learns. Frist the machine gathers information and knowledge then use those knowledge to take decisions. Also, past experiences helps to take decisions in future.

What is Deep Learning(DL) or Deep Neural Network(DNN)?

-          Deep Learning(DL) is part of a broader family of Machine Learning and AI, which emulate the learning approach that human beings use to gain certain types of knowledge. Traditionally machine learning algorithms used to be linear, but with deep learning algorithms are stacked in a hierarchy of increasing complexity and abstraction. Because this process mimics a system of human neurons, deep learning is sometimes referred to as Deep Neural Learning(DNN) or deep neural networking. Let me explain the concept with an example blow-

-          A baby when starts learning about what a cat is (and is not) by pointing to some objects and saying the word cat. The parent guides him by saying, "Yes, that is a cat," or, "No, that is not a cat." As the baby continues to point to objects, he becomes more aware of the features that all cat have. What the baby does, without knowing it, is clarify a complex abstraction by building a hierarchy in which each level of abstraction is created with knowledge that was gained from the preceding layer of the hierarchy. A machine follows more or less similar approach. Each algorithm in the hierarchy applies a nonlinear transformation on its input and uses what it learns to create a statistical model as output. Iterations continue until the output has reached an acceptable level of accuracy. The number of processing layers through which data must pass is what inspired the label deep.

What is Natural Language Processing(NLP)?

-          Natural Language Processing is the ability of a computer program to understand human languages as it is spoken. NLP is also component of AI. The development of NLP is challenging because traditionally computer requires human to speak to them in a programming language or unambiguous or highly structured, clear commands. Whereas natural languages are generally ambiguous, have different structures, dialects, regional effects which are difficult to distinguish.

-          Semantic analysis and Natural Language Processing can help machines automatically understand text, which supports the even larger goal of translating information, understanding potentially valuable piece of customer feedback, understanding insight in a tweet or in a customer service log into the realm of business intelligence for customer support, corporate intelligence or knowledge management.

What is Computer Vision and Image Processing?

-          Computer vision is about granting the computer the ability to ‘see’ and ‘understand’ what it sees. In image processing you get an image as input and provide processed image as output, whereas in computer vision you get an image (or video) as input and provide other quantitative data as an output (e.g geometrical information about the objects in question). Computer Vision tries to do what a human brain does with the retinal input, it includes understanding and predicting, detecting certain things. For example, given an input image, using computer vision the computer can classify the objects (cars,humans,train.. etc) as human does. There are many other applications but this is just to give you a basic idea.

  This was the basic concepts. Please comment below if you have any questions or feedback. Stay tuned for more detailed concepts of Machine Learning Algorithms.

Next topic is Supervised, Un-Supervised, Semi-Supervised machine and Reinforcement Learning algorithms