Page 136 - Ai Book - 10

implementing neural networks on high dimensional data to gain insights and form solutions. The development
of self-driving cars requires millions of images and thousands of hours of video is a great example of deep
learning.

Difference Between Artificial Intelligence, Machine Learning and Deep Learning
In general, Artificial Intelligence is a branch of computer science that is made up of two main terminologies:
Machine Learning and Deep learning. Machine learning is a subfield of AI whereas deep learning is the subfield
of Machine learning. The main difference among these three technical terms are as follows:

S. No Basis Artificial Intelligence Machine Learning Deep Learning
1 Learning Power AI enables machines to The Machine Deep learning or deep
think without any human Learning systems neural learning is a subset
intervention. can automatically of machine learning
learn and improve techniques. Deep learning
without explicitly being systems are capable of
programmed. learning by example.
2 Applications The main applications Product Driverless Cars and
of AI are Siri, customer recommendation Autonomous vehicles
support using catboats, engine used by various are examples of Deep
Expert System, Online e-commerce websites is Learning Systems.
game playing, intelligent an example of Machine
humanoid robot, etc. learning systems.
3 Data Dependencies AI systems give excellent Machine Learning Deep learning
performance on a big systems give excellent systems give excellent
dataset. performances on a performance on a big
small/medium dataset dataset.
4 Data Type The data required by AI The data required The data required by
systems can be either by Machine learning Deep Learning systems
Structured, Unstructured systems is mostly in can be either structured
or Semi-Structured. structured form. or unstructured because
they rely on the layers
of the Artificial neural
network.
5 Problems/ Tasks AI systems are able to Machine learning Deep learning models
perform various complex models are suitable for are suitable for solving
problems. solving simple or bit- complex problems.
complex problems.

10
10