What is Deep Learning and how is it different from Machine Learning an

What is Deep Learning and how is it different from Machine Learning and Representative Learning?

Answer»

DEEP Learning is a BRANCH of machine learning based on a set of ALGORITHMS that attempt to model high level and hierarchical representation in data using deep graph with multiple processing layers, multiple linear and non-linear transformations.

In Machine Learning (ML), basic process flow is from “INPUT” to “hand designed features” to “mapping from features” to “output”. In Representation Learning (RL), basic process flow is from “Input” to “features” to “mapping from features” to “output”. In Deep Learning (DL), basic process flow is from “Input” to “ simple features” to “more layers of abstract features” to “mapping from features” to “output”. Below table provides a quick REFERENCE of this understanding.

Topic / Area	Basic Process Flow
Machine Learning	Input

Discussion

No Comment Found

Related InterviewSolutions

What is the output of the program below? Assume that it is being executed using Python 3.x environment. Will the session close automatically or remain open at the end of the program.
What is Artificial Neural Network (ANN and what is a perceptron algorithm? Mention few R packages for ANNs.
What is deep learning platform and deep learning library? Explain with examples from each.
Image classification and taggingSentiment analysisFace detectionVideo recognitionSpeech recognition
Which of the following are use cases of machine vision. Select all that apply.
What is a Convolutional Neural Network (CNN)? Describe with a diagram about its architecture and typical layer components. Does it perform dimensionality reduction – if yes, which layer/component?
d) All of the above.
c) The gradient is calculated multiplying two numbers between 0 and 1
b) With backpropagation, the gradient becomes smaller as it works back through the net
a) Training is quick if the gradient is large and slow if it is small