Comparison of Machine Learning and Deep Learning

Machine Learning vs Deep Learning

Machine Learning - 

Machine Learning is the subset of AI (Artificial Intelligence) used to build models that learn and improve from the data provided to it without being explicitly programmed for it. The models are trained on a lot of data. The trained model performs on the new data and is expected to give the same or better outputs. It is used for speech recognition and image recognition.

Deep Learning - 

Deep Learning is the subset of ML (Machine Learning) consisting of different types of Neural Networks such as Artificial Neural Network (ANN) and Convolutional Neural Network (CNN)  which are made up of a number of layers depending on the model which learns from each other. It is inspired by the functioning of the human brain and tries to mimic the working of the brain. It is used for more complex problems like the automation of vehicles, visual recognition, and virtual assistants.

 

Different types of Machine Learning Algorithms :

1. Regression Algorithms

1.  Simple Linear Regression
2.  Multiple Linear Regression
3.  Polynomial Regression
4.  Support Vector Regression
5.  Decision Tree Regression
6.  Random Forest Regression

2.  Classification Algorithms

1.  Logistic Regression
2.  K-Nearest Neighbors (KNN)
3.  Support Vector Machine (SVM)
4.  Kernel SVM
5.  Naive Bayes
6.  Decision Tree Classification
7.  Random Forest Classification

3.  Clustering Algorithms

1.  K-means Clustering
2.  Hierarchial Clustering

4. Association Rule Learning

1. Apriori
2. Eclat
3. F-P Growth Algorithm

4. Reinforcement Learning

1. Upper Confidence Bound (UCB)
2. Thompson Sampling

Different types of Deep Learning Algorithms :

1. Artificial Neural Networks

2. Convolutional Neural Networks

3. Recurrent Neural Networks

4. Self Organizing Maps

4. Boltzmann Machines

5. Autoencoders

Key comparisons between Machine learning and Deep learning:

Machine Learning	Deep Learning
Machine Learning is a subset of Artificial Intelligence (AI).	Deep Learning is a subset of Machine Learning (ML).
Machine Learning grew out of work in AI. It is an evoulution of AI.	Deep Learning grew out of work in ML. It is an evoulution of ML.
Machine Learning models can be trained on thousands of data points. It requires lesser data.	Deep learning models are trained on millions of data points i.e. Big Data.
Feature extraction needs to be done for machine learning models.	Deep learning models learn about features on its own from the data.
They can work on low end machines since they work on less amount of data.	They need high end machines with GPU because they require big data for efficient working..
Machine Learning algorithms require less amount of time for execution.	Deep learning algorithms takes a lot of time to train the model.
They are used for solving mostly simple or bit-complex problems.	They are used for solving mostly complex problems.
They mostly requires data in a structured format.	They don't need specifically as such because they rely on the layers.
It uses different types of automated algorithms that turn to model functions and predict outputs from the given data.	It uses neural networks for finding the relations between the data points and for feature extraction.