AI, ML, and DL: How not to get them mixed

Ref. https://towardsdatascience.com/understanding-the-difference-between-ai-ml-and-dl-cceb63252a6c

Understanding difference between Artificial Intelligence, Machine Learning and Deep Learning

I am pretty sure most of us might be familiar with the term “ Artificial Intelligence”, as it has been a major focus in some of the famous Hollywood movies like “The Matrix”, “The Terminator” , “Interstellar”. Although Hollywood films and science fiction novels portray AI as human-like robots taking over the planet, the actual evolution of AI technologies is not even that smart or that frightening. Instead AI has grown to offer many different benefits across industries like healthcare, retail, manufacturing, banking and many more.

Artificial Intelligence, Machine Learning, Deep Learning, Data Science are popular terms in this era. And knowing what it is and the difference between them is more crucial than ever. Although these terms might be closely related there are differences between them see the image below to visualize it.

Photo by Author

What is Artificial Intelligence?

Humans have long been obsessed with creating AI ever since the question, “Can machines think?”, was posed by Alan Turing in 1950. AI enables the machine to think, that is without any human intervention the machine will be able to take its own decision. It is a broad area of computer science that makes machines seem like they have human intelligence. So it’s not only programming a computer to drive a car by obeying traffic signals but it’s when that program also learns to exhibit the signs of human-like road rage.

Image from Artificial Intelligence HubSpot

Types of Artificial Intelligence System

AI systems are classified by their ability to imitate human behaviors, the hardware they use to do so, their applications in the real world and the theory of mind. Using these features for comparison, all systems of artificial intelligence actual and hypothetical fall into one of three types:

ANI: Artificial Narrow Intelligence

Artificial Narrow intelligence is also known as weak AI and it is the only type of AI that exists in our world today. Narrow AI is goal oriented and is programmed to perform a single task and is very intelligent in completing the specific task that it is programmed to do. Some examples of ANI are Siri, Auto pilot in an airplane, chat bots, self driving cars etc.

Narrow AI systems are not conscious, sentient or driven by emotions as humans are, they use information from a specific dataset and do not perform any task that is outside of the single task that they are designed to perform.

AGI: Artificial General Intelligence

Artificial General Intelligence also referred to as strong AI is a concept in which machines exhibit human intelligence. In this the machines have the ability to learn, understand and act in a way that is indistinguishable from a human in a given situation. The General AI does not currently exist but has been used in many sci-fi hollywood movies in which the humans interact with machines that are conscious, driven by emotions and self-aware.

Using strong AI we can have the ability to build machines that can think, strategize and perform multiple tasks under uncertain conditions. They can integrate their prior knowledge in decision making to come up with innovative, creative and unconventional solutions.

ASI: Artificial Super Intelligence

I am sure you remember Arnold Schwarzenegger’s “The Terminator” where a machines cognizance superseded human intelligence in all aspects. Artificial Super Intelligence is a hypothetical AI where machines will be capable of exhibiting intelligence that surpasses that of the brightest humans. In this type of AI, apart from having multifaceted intelligence of human beings machines will have greater problem solving and decision making capabilities that will be far superior than human beings. It is the type of AI that will have great impact on humanity and may lead to extinction of the human race from the planet.

What is Machine Learning?

Machine Learning is a subset of Artificial Intelligence that uses statistical learning algorithms to build systems that have the ability to automatically learn and improve from experiences without being explicitly programmed.

Most of us use machine learning in our day to day life when we use services like recommendation systems on Netflix, Youtube, Spotify; search engines like google and yahoo; voice assistants like google home and amazon alexa. In Machine Learning we train the algorithm by providing it with a lot of data and allowing it to learn more about the processed information.

ML algorithms can be broadly classified into three categories Supervised, Unsupervised and Reinforcement learning.

Supervised Learning

In supervised learning we have input variables (x) and an output variable (Y) and we use an algorithm to learn the mapping from input to output. In other words, a supervised learning algorithm takes a known set of input dataset and its known responses to the data (output) to learn the regression/classification model. A learning algorithm then trains a model to generate a prediction for the response to new data or the test datasets.

Unsupervised Learning

Unsupervised Learning is used when we do not have labelled data. Its main focus is to learn more about the data by inferring patterns in the dataset without reference to the known outputs. It is called unsupervised because the algorithms are left on their own to group the unsorted information by finding similarities, differences and patterns in the data. Unsupervised learning is mostly performed as a part of exploratory data analysis. It is most commonly used to find clusters of data and for dimensionality reduction.

Reinforcement Learning

In simple terms, reinforcement learning can be explained as learning by continuously interacting with the environment. It is a type of machine learning algorithm in which an agent learns from an interactive environment in a trial and error way by continuously using feedback from its previous actions and experiences. The reinforcement learning uses rewards and punishments, the agents receive rewards for performing correct actions and penalties for doing it incorrectly.

What is Deep Learning?

Deep learning is a machine learning technique that is inspired by the way a human brain filters information, it is basically learning from examples. It helps a computer model to filter the input data through layers to predict and classify information. Since deep learning processes information in a similar manner as a human brain does, it is mostly used in applications that people generally do. It is the key technology behind driver-less cars, that enables them to recognize a stop sign and to distinguish between a pedestrian and lamp post. Most of the deep learning methods use neural network architectures, so they are often referred to as deep neural networks.

Deep Learning is basically mimicking the human brain, it can also be defined as a multi neural network architecture containing a large number of parameters and layers. The three fundamental network architectures are as listed below:

Convolutional Neural Networks

Image from MDPI article Entropy 19.6 (2017): 242

Convolutional Neural Network is basically an artificial neural network that is most widely used in the field of Computer Vision for analyzing and classifying images. It is a deep learning algorithm that takes the input image and assigns weights/biases to various aspects or objects in the image, so that it can differentiate one from the other. The hidden layers of a CNN typically consist of convolutional layers, pooling layers, fully connected layers, and normalization layers. The architecture of a ConvNet is analogous to that of the connectivity pattern of Neurons in the Human Brain and was inspired by the organization of the Visual Cortex.

Recurrent Neural Networks

Recurrent Neural Networks is a type of neural network architecture that is used in sequence prediction problems and is heavily used in the field of Natural Language Processing. RNNs are called recurrent because they perform the same task for every element of a sequence, with the output being dependent on the previous computations. Another way to think about RNNs is that they have a “memory” which captures information about what has been calculated so far.

To understand more about RNN please refer this article

http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/

Recursive Neural Networks

“A recursive neural network is a kind of deep neural network created by applying the same set of weights recursively over a structured input, to produce a structured prediction over variable-size input structures, or a scalar prediction on it, by traversing a given structure in topological order.” [9]

A recursive neural network is more like a hierarchical network where there is really no time aspect to the input sequence but the input has to be processed hierarchically in a tree fashion. Here is an example of how a recursive neural network looks. It shows the way to learn a parse tree of a sentence by recursively taking the output of the operation performed on a smaller chunk of the text.

Screenshot from PyTorch — Recursive Neural Networks — Tutorialspoint

This article tries to explain the differences between Artificial Intelligence, Machine Learning and Deep Learning, by defining them and explaining the various subcategories within each topic. To get a deeper understanding of the above mentioned topics please refer to the articles mentioned in the references section.

References

1. http://beamandrew.github.io/deeplearning/2017/02/23/deep_learning_101_part1.html
2. https://contentsimplicity.com/what-is-deep-learning-and-how-does-it-work/
3. https://towardsdatascience.com/what-are-the-types-of-machine-learning-e2b9e5d1756f
4. https://codebots.com/artificial-intelligence/the-3-types-of-ai-is-the-third-even-possible
5. https://www.sciencedirect.com/topics/computer-science/supervised-learning
6. https://medium.com/@tjajal/distinguishing-between-narrow-ai-general-ai-and-super-ai-a4bc44172e22
7. https://towardsdatascience.com/understanding-neural-networks-from-neuron-to-rnn-cnn-and-deep-learning-cd88e90e0a90
8. https://en.wikipedia.org/wiki/Recursive_neural_network
9. https://www.youtube.com/watch?v=k2P_pHQDlp0&t=404s