Machine learning and Deep learning are concepts that fall under the umbrella of artificial intelligence (AI); AI is a field of science dedicated to making machines think and act like humans.
The concept of Machine Learning is to set up computers to be able to conduct tasks without the need for explicit programming efficiently. These computers are typically fed structured data for them to “learn” from and become better at evaluating, predicting, and acting on that data over time. This is also known as supervised learning.
Deep Learning is a subset of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks. The neural network consists of 3 or more layers (input, hidden, output) that try to simulate the behavior of a human brain by “learning” from large unstructured data sets. This is also known as unsupervised learning.
Differences between Machine Learning & Deep Learning:
| Machine Learning | Deep Learning | |
| Type of Learning | Supervised | Unsupervised |
| Data Type | Structured | Unstructured |
| Training Time | Short (secs to hours) | Long (days to weeks) |
| Hardware Requirements | Computers with CPU | Computers with GPU |
| No. of algorithms | Many | Few |
| Accuracy | Medium to low accuracy | Very high accuracy |
| Problem Solving | Divides large problems into sub-problems & then results are combined at the end for one conclusion | DL resolves larger problems on an end-to-end basis without any extra intervention. |
| Implementation Costs | Low to moderate | Moderate to high |
