Saroj Jha

With the increase in dependence on technology in our daily lives, we are gradually more relying on learning quicker and faster algorithms to make things easier. These technologies are commonly associated with artificial intelligence, machine learning, deep learning, and neural networks, and these terms tend to be used conversely, leading to some confusion.

Let's make it clear: artificial intelligence (AI), machine learning (ML), and deep learning (DL) are three different things. To illustrate, the picture below shows machine learning is a subfield of artificial intelligence, deep learning is a subfield of machine learning, and neural networks make up the backbone of deep learning algorithms.

Artificial intelligence is the broadest term used to classify machines that mimic human intelligence. It can be used to build intelligent programs and machines that can predict, automate, and optimize tasks that have always been considered a human prerogative. AI use cases exist across every industry, and some of the most prevalent today include:

• Image recognition – e.g., automated social media photo tagging
• Video classification – e.g., a security camera detecting an intruder
• Speech-to-text – e.g., dictating to your smartphone while driving
• Natural language processing – e.g., text analytics, sentiment analysis, chatbots
• Recommendation systems – e.g., personalized advertising, product reviews
• Tabular and time-series data applications – e.g., financial analysis, email spam filters, smart wireless network routing

There are three main categories of AI defined by its ability compared to humans:

• Artificial Narrow Intelligence (ANI): ANI is considered "weak" AI, whereas the other two types are classified as "strong" AI. Weak AI is defined by its ability to complete a very specific task, like winning a chess game or identifying a specific individual in a series of photos.
• Artificial General Intelligence (AGI) would perform on par with other human
• Artificial Super Intelligence (ASI) also known as superintelligence—would surpass a human's intelligence and ability.

"Strong" AI seeks to create machines that have all the mental powers humans have, including phenomenal consciousness. "Weak" AI, on the other hand, seeks to build information-processing machines that appear to have the full mental repertoire of human persons (Searle 1997)."

Machine learning is a subset of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning is a class of statistical methods that use parameters from known existing data and then predicts outcomes on similar novel data. For example, given the history of home sales in a city, you could use machine learning to create a model that can predict how much a different home in that same city might sell for.

Traditionally, machine learning relies on a prescribed set of "features" that are considered important within the dataset. For example, features relevant to a home's price might be the number of bedrooms in the home, the size of the home in square feet, and standardized test scores in the school district. The process of building features into a machine learning algorithm is known as "feature engineering." Feature engineering requires deep expertise in a given subject (here, residential real estate) and can be quite a labor-intensive process for the data scientist.

In ML, there are different algorithms (e.g. neural networks) that help to solve problems. So, based on how they learn, machine learning algorithms are usually divided into 4 groups:

Supervised Learning

"Supervised" means that a teacher helps the program throughout the training process: there is a training set with labeled data. For example, you want to teach the computer to put red, blue, and green socks into different baskets. First, you show to the system each of the objects and tells what is what. Then, run the program on a validation set that checks whether the learned function was correct. The program makes assertions and is corrected by the programmer when those conclusions are wrong. The training process continues until the model achieves a desired level of accuracy on the training data. This type of learning is commonly used for classification and regression.

Algorithm examples:

• Naive Bayes,
• Support Vector Machine,
• Decision Tree,
• K-Nearest Neighbours,
• Logistic Regression,
• Linear and Polynomial regressions.

Used for: spam filtering, language detection, computer vision, search, and classification.

Unsupervised Learning

In unsupervised learning, you do not provide any features to the program allowing it to search for patterns independently. Imagine you have a big basket of laundry that the computer has to separate into different categories: socks, T-shirts, jeans. This is called clustering, and unsupervised learning is often used to divide data into groups by similarity.

Algorithm examples:

• K-means clustering,
• DBSCAN,
• Mean-Shift,
• Singular Value Decomposition (SVD),
• Principal Component Analysis (PCA),
• Latent Dirichlet allocation (LDA),
• Latent Semantic Analysis, FP-growth.

Used for: segmentation of data, anomaly detection, recommendation systems, risk management, fake image analysis.

Semi-supervised Learning

Semi-supervised learning means that the input data is a mixture of labeled and unlabeled samples. The programmer has in mind the desired prediction outcome but the model must find patterns to structure the data and make predictions itself.

Reinforcement Learning

This is very similar to how humans learn: through trial. Humans don't need constant supervision to learn effectively like in supervised learning. By only receiving positive or negative reinforcement signals in response to our actions, we still learn very effectively. For example, a child learns not to touch a hot pan after feeling pain. One of the most exciting parts of Reinforcement Learning is that it allows you to step away from training on static datasets. Instead, the computer can learn in dynamic, noisy environments such as game worlds or the real world.

Used for: self-driving cars, games, robots, resource management.

Deep learning, or deep neural learning , is a subset of machine learning, which uses neural networks to analyze different factors with a structure that is similar to the human neural system.

Deep learning is a type of machine learning that has received increasing focus in the last several years. With deep learning, the algorithm doesn't need to be told about the important features. Instead, it can discover features from data on its own using a "neural network." The name is inspired by a mathematical object called an artificial neuron that "fires" if the combination of inputs exceeds some threshold, just like a neuron in the brain does. Artificial neurons can be arranged in layers, and deep learning involves a "deep" neural network (DNN) that has many layers of artificial neurons.

Many fundamental deep learning concepts have been around since the 1940s, but several recent developments have converged to supercharge the current deep learning revolution. These developments include:

Bigger datasets – The scale of available data has increased dramatically, providing enough input to develop accurate models. For example, ImageNet is an open dataset of 10 million hand-labeled images, and Google's parent Alphabet has released eight million YouTube videos with category labels.

Better hardware – Training a typical deep learning model may require 10 exaflops (1018, or one quintillion, floating-point operations) of computing. Due to Moore's Law, hardware now exists that can perform this task cost- and time-effectively.

Smarter algorithms – Cloud service providers such as Google and Amazon have realized the value of AI and are investing heavily in fundamental research in the field. New algorithms are constantly being published, and most work is freely available.

The result has been an explosion of AI products and startups, and accuracy breakthroughs in image and speech recognition. Thanks to deep learning, machines now routinely demonstrate better than human-level accuracy. Deep learning is why Facebook is so good at recognizing who is in the photo you just uploaded and why Alexa generally gets it right when you ask her to play your favorite song.