Difference between Machine Learning, Deep Learning and Artificial Intelligence
By- Rachit Kumar Agrawal
John McCarthy, widely recognized as one of the godfathers of Artificial Intelligence (AI), defined AI as “the science and engineering of making intelligent machines that have the ability to achieve goals like humans do” in the year 1955. In short, Artificial Intelligence is human intelligence exhibited by Machines.
Arthur Samuel defined Machine Learning (ML) in 1959 as a large sub-field of AI dealing with the field of study that gives computers the ability to learn without being explicitly programmed. This means a single program, once created, will be able to learn how to do some intelligent activities outside the notion of programming. This contrasts with purpose-built programs whose behavior is defined by hand-crafted heuristics that explicitly and statically define their behavior. So, you can say Machine Learning is an approach to achieve Artificial Intelligence.
Fig 1. Illustrates how a machine learning model learns:
This is exactly how humans learn as well. When any kid learns to identify objects/person, we don’t tell them an algorithm/procedure to identify the features and then decide what is it. We simply show them multiple examples of that object and then our human brain automatically identifies the features (sub-consciously) and learns to identify that object. This is indeed what a Machine Learning Model does.
Within the machine learning fields, there is an area often referred to as brain-inspired computation. Human brain is one of the best ‘machine’ we know for learning and solving problems. The brain-inspired technique is indeed inspired by how our human brain works. It is believed that the main computational element of our brain is neuron. The complex connected network of neurons forms the basis of all the decisions made based on the various information gathered. This is exactly what Artificial Neural Network technique does.
Within the domain of neural networks, there is an area called Deep Learning(DL), in which neural networks have more than three layers, i.e. more than one hidden layer. These neural networks used in Deep learning are called Deep Neural Networks (DNNs).
So, Deep Learning is a technique for implementing Machine Learning. Thanks to Deep learning, there are many tasks that machines can now do better than humans. One such example is image classification. In 2015, the ImageNet winning entry, ResNet, exceeded human-level accuracy with a top-5 error rate below 5%. Humans can classify images with error rate 5%.
Fig. 2 illustrates the relationship between Artificial Intelligence, Machine Learning and Deep Learning. If you look at it from the mathematical terms, all machine learning is AI, but not all AI is machine learning. Similarly, all deep learning is machine learning but not all machine learning is deep learning.
To summarize:
· Artificial Intelligence is human intelligence exhibited by machines
· Machine Learning is an approach to achieve Artificial Intelligence
· Deep Learning is a technique for implementing Machine Learning
Master these revolutionary technologies today with Udacity
About the Author | Rachit Kumar Agrawal
A Deep Learning Researcher by profession who loves to “train” his mind by learning new stuffs and loves to watch Formula 1 and do social work in free time.
