This post is a modified excerpt from one of my publications on machine learning. Everyone is curious and the jargon doesn’t get off our backs. I attempted a comparison between the prevalent terminologies that exist today and how each of these are similar or dissimilar to machine learning. Please remember, I haven’t yet brought in the Cognitive computing to the mix. My next post will cover more on cognition and how it is different from other areas of learning / intelligence.
[embed]https://www.datadriveninvestor.com/2019/01/23/deep-learning-explained-in-7-steps/[/embed]
Firstly, machine learning, it is a way of letting the machine learn from the data provided to it as against hand coding the rules. The concept map below depicts various aspects of machine learning.
Before we start comparing these terms, first let us look at different categories of learning methods in machine learning.
Among all the learning methods, deep learning is a sub-field of machine learning and focuses on algorithms that are built on the model that the human brain is built and solves problems typically the way humans solve. Deep learning is an area of Machine learning that focuses on unifying Machine learning with artificial intelligence. Regarding the relationship with artificial neural networks, this field is more of an advancement to artificial neural networks that work on large amounts of common data to derive practical insights. It deals with building more complex neural networks to solve problems classified under semi-supervised learning and operates on datasets that have little labeled data. Some Deep learning techniques are listed as follows:
Convolutional Networks
Restricted Boltzmann Machine (RBM)
Deep Belief Networks (DBN)
Stacked Autoencoders and others
A quick insight into what comprises deep learning is shown in the concept map below.
Artificial intelligence focuses on building systems that can mimic human behavior. It has been around for a while now, and the modern AI has been continuously evolving, now including specialized data requirements. Among many other capabilities, AI should demonstrate the following:
Knowledge storage and representation to hold all the data that is subject to interrogation and investigation
Natural Language Processing (NLP) capabilities to be able to process text
Reasoning capabilities to be able to answer questions and facilitate conclusions
The ability to plan, schedule, and automate
Machine learning to be able to build self-learning algorithms
Robotics and more
Originally published at https://www.linkedin.com. [embed]https://upscri.be/b2a0d6/[/embed]