Demystifying Artificial Intelligence (AI)

Artificial Intelligence (AI)

Artificial Intelligence (AI) was coined by John McCarthy, an American computer scientist, in 1956 at The Dartmouth Conference where the discipline was born. AI is a term for simulated intelligence in machines, especially computer systems. These machines are programmed to "think" like a human and mimic the way a person acts. The ideal characteristic of artificial intelligence is its ability to rationalize and take actions that have the best chance of achieving a specific goal, although the term can be applied to any machine that exhibits traits associated with a human mind, such as learning and solving problems. AI is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think. It is a science and technology based on disciplines such as Computer Science, Biology, Psychology, Linguistics, Mathematics, Sociology and Engineering.

The AI Landscape

Machine Learning (ML)

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves.

Types of Machine Learning (ML)

• Supervised Learning
• Task Driven (Predict Next Value)
• Problems solved with supervised learning can be further broken down into classification and regression problems
• Unsupervised Learning (UL)
• Data Driven (Identify Clusters)
• Unsupervised learning can be grouped into clustering and association problems
• Reinforcement Learning / Deep Reinforcement Learning (DRL)
• Reward Driven (Learn from Mistakes)

Common Machine Learning (ML) Algorithms

• Supervised Learning
• Nearest Neighbor
• Naive Bayes
• Decision Trees
• Linear Regression
• Support Vector Machines (SVM)
• Neural Networks
• Unsupervised Learning
• K-means clustering
• Association Rules
• Reinforcement Learning
• Q-Learning
• Temporal Difference (TD)
• Deep Adversarial Networks

Deep Learning (DL)

Deep Learning is a sub-field of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks. Deep learning usually consists of multiple layers. They typically combine simpler models to build more complicated ones by passing along data from one layer to another; which is one of the primary reasons deep learning outperforms other learning algorithms as the amount of data increases.

Neural Networks (NN)

A Neural Network (NN) is a system of hardware and/or software patterned after the operation of neurons in the human brain. Also called Artificial Neural Networks are a variety of deep learning technologies. Commercial applications of these technologies generally focus on solving complex signal processing or pattern recognition problems.

Convolutional Neural Networks (CNN)

In machine learning, a Convolutional Neural Network is a class of deep, feed-forward artificial neural networks that has successfully been applied to analyzing visual imagery.

Recurrent Neural Network (RNN)

A Recurrent Neural Network (RNN) is a class of artificial neural network where connections between units form a directed graph along a sequence.

Generative Adversarial Networks (GAN)

Generative Adversarial Networks (GAN) are neural networks that are trained in an adversarial manner to generate data mimicking some distribution.

Natural Language Processing (NLP)

Natural language processing (NLP) is the ability of a computer program to understand human language as it is spoken.

Dynamic Memory Networks (DMN)

A Dynamic Memory Network (DMN) is a neural network architecture optimized for question-answering (QA) problems. Given a training set of input sequences (knowledge) and questions, it can form episodic memories, and use them to generate relevant answers.

AI Infrastructure (Data Analytics Process)

Introduction to Keras

Keras is a simple, high-level neural networks library, written in Python that works as a wrapper to Tensorflow. It is a self-contained framework for deep learning. One can use Keras to solve problems end-to-end without ever having to interact with the underlying back-end engine TensorFlow.

Introduction to TensorFlow

TensorFlow is a Python library for fast numerical computing that was designed specifically for machine learning. It was open-sourced by Google with the hope of putting deep learning capabilities in the hands of a lot more researchers and developers around the world.

Three Stages of AI

The AI Periodic Table

​Thinking about Artificial Intelligence has proven to be difficult, people argue constantly about what is and is not AI. Have difficultly deciding what technologies should be included within it, and researchers struggle with how to evaluate it, in order to avoid imposing any architecture on these components, they have structured this exploration around individual elements that can be pulled together in different ways depending on the need, thus a Periodic Table of AI. Of course, this table is the start, not the end. Over time, the elements will be refined and expanded upon and the table itself reorganized.

<!> Reference Sources: International Institute of Executive Careers (IIEC) course material for Certified Artificial Intelligence Professional™ (CAIP), AI, ML, DL, Training Videos, Google Images.