AI / ML

What is Artificial Intelligence? The answer to this question would depend on who you ask.

A layman, with a fleeting understanding of technology, would link it to robots. If you ask about artificial intelligence to an AI researcher, he/she would say that it’s a set of algorithms that can produce results without having to be explicitly instructed to do so. Both of these answers are right. Artificial Intelligence (AI) covers a range of techniques that appear as sentient behavior by the computer. Even though AI is already creating tremendous amounts of value into software industry, a lot of the value to be created in a future lies outside the software industry. In sectors such as retail, travel, transportation, automotive, materials, manufacturing and so on. For example, AI is used to recognize faces in photographs on your social media, beat the World’s Champion in chess, and process your speech when you speak to Siri or Alexa on your phone. Currently, Artificial Intelligence is shared by all the different tools and techniques have been invented by us over the last thousand years – to simplify human effort, and to help us make better decisions. Artificial Intelligence is one such creation that will help us in further inventing ground-breaking tools and services that would exponentially change how we lead our lives, by hopefully removing strife, inequality and human suffering.

Supervised learning is currently the most common type of machine learning.

A computer is provided with labeled examples (e.g., photos of cars with text labels of the manufacturers). The machine attempts to correctly label any new image presented without actually memorizing every pair it trained on.

Supervised learning is analogous to training a child to walk. You will hold the child’s hand, show him how to take his foot forward, walk yourself for a demonstration and so on, until the child learns to walk on his own. Similarly, in the case of supervised learning, you give concrete known examples to the computer.

In the case of supervised learning, you give concrete known examples to the computer. You say that for given feature value x1 the output is y1, for x2 it is y2, for x3 it is y3, and so on. Based on this data, you let the computer figure out an empirical relationship between x and y. This set of AI called supervised learning, just learns input to output, or A to B mappings. On one hand, input to output, A to B it seems quite limiting. But when you find a right application scenario, this can be incredibly valuable. 

Unsupervised learning is less common than supervised learning. In this type of Machine Learning, a computer is provided with no training labels.

In unsupervised learning, we do not specify a target variable to the machine, rather we ask machine “What can you tell me about X?”. More specifically, we may ask questions such as given a huge data set X, “What are the five best groups we can make out of X?” or “What features occur together most frequently in X?”. To arrive at the answers to such questions, you can understand that the number of data points that the machine would require to deduce a strategy would be very large. In case of supervised learning, the machine can be trained with even about few thousands of data points. However, in case of unsupervised learning, the number of data points that is reasonably accepted for learning starts in a few millions. These days, the data is generally abundantly available. The data ideally requires curating. However, the amount of data that is continuously flowing in a social area network, in most cases data curation is an impossible task.

One common technique is clustering — finding reasonable groupings between data points automatically. 

Reinforcement Learning is a type of Machine Learning that lets a computer learn through trial and error by attempting to maximize rewards.

This technique was initially developed for machines to play games. The machine is given an algorithm to analyze all possible moves at each stage of the game. The machine may select one of the moves at random. If the move is right, the machine is rewarded, otherwise it may be penalized. Slowly, the machine will start differentiating between right and wrong moves and after several iterations would learn to solve the game puzzle with a better accuracy. The accuracy of winning the game would improve as the machine plays more and more games.

E.g., a machine can learn to play a video game with an objective of getting the highest score possible. Over time, the machine will perform better and better.

Deep learning is a Machine Learning technique that teaches computers to do what comes naturally to humans: learn by example. Deep Learning mimics structures in the human brain. By layering multiple neurons together, each can focus on specific aspects of a stimulus (e.g., the shape, color, and opacity of an object in an image). Increasing the number of layers generally increases the power and time required, as well as the accuracy.

In Deep Learning, a computer model learns to perform classification tasks directly from images, text, or sound. Deep learning models can achieve accuracy, sometimes exceeding human-level performance. Models are trained by using a large set of labeled data and neural network architectures that contain many layers.

Deep learning is a key technology behind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost. It is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free speakers.

A neural network is a computer system inspired by the design of an organic brain.

A neural network is a series of algorithms that recognize the underlying relationships in a set of data through a process that mimics the way the human brain operates. Using algorithms, they can recognize hidden patterns and correlations in raw data, cluster and classify it, and continuously learn and improve over time.

Neural Networks are regulating some key sectors including finance, healthcare, and automotive. As these artificial neurons function in a way similar to the human brain. They can be used for image recognition, character recognition and stock market predictions. 

Transfer learning is an attempt to build more generally applicable Artificial Intelligence by taking knowledge/models from one task and applying it to a different task.

A machine that becomes an expert in one task may be able to transfer what it has learned to another.