Artificial Intelligence Vs. Machine Learning Vs. Deep Learning !

AI textbooks define AI as “The Study and Design of Intelligent Agents” where an intelligent agent is a system that perceives its environment and takes actions that maximize the chances of its success.
The Capability of Machine to simulate and Imitate Intelligent Human Behavior is Artificial Intelligence



Application of AI:  Some examples borrowed from Course Era

    1. Movie/ Songs recommendation
    2. Fraud Detection – credit card purchases
    3. Smart home devices
    4. Facebook – tagging friends
    5. Video Games
    6. Virtual Personal Assistants: Siri, Cortana

The brain behind AI is the Machine Learning , Deep Learning and Natural Language Processing (NLP).
Some scientist classify NLP as Deep Learning and some scientist classify NLP as Machine Learning.




Important Components of Deep Learning and Machine Learning.
(NLP will be covered in the following post)




Lets start with Data:

As seen below the type of Statistical Methods keep changing with DATA COMPLEXITY
As the data complexity increases - there is a shift from Traditional Statistical Methods to Small Neural Network to Medium Neural Network and then Large Neural Network 




Algorithms : They can be Machine Learning or Deep Learning Algorithms

What is Machine Learning:

          Algorithms that do the learning without human intervention.    
          Supervised Learning: Learning with a labeled training set (cases are labelled as – spam / no spam  ,  fraud /no  fraud already available in the training data-set )
          Unsupervised Learning : Discover patterns in unlabeled data (labeling of cases not available)
          Optimize parameters on training data using Gradient Descent Computation
          Goal of Machine learning –minimization of error (predicted – actual).

Machine Learning Algorithms:

  Linear Regression
  Logistic Regression
 Cluster Analysis
 Support Vector Machine
 Shallow Neural Network
  Principal Component Analysis
 Recommend-er System
 Anomaly Detection /Outlier detection

Now let us take the example of shallow neural network .
The below  neural network with one hidden layer is shallow neural network or simple neural network that falls under Machine Learning





Why is Deep Learning Taking of?
Need for Deep Learning arise when the data complexity increases.
Complex Neural Network falls under Deep learning
A complex neural network is  Deep Learning as shown below

A deep neural network with many hidden layers falls under DEEP LEARNING



Applications of Deep Learning





Computation :

Mathematical computation is required to derive co-efficient / parameter estimates / Weights for the Model.
Co-efficient is derived using Differential Calculus , the technique is known as - "Gradient Descent"
Both the Machine Learning and Deep Learning Algorithm uses  "Gradient Descent" for Computation of co-efficient.
All algorithms needs computation of parameter estimates which is done using a differential calculus technique called as - "Gradient Descent"



So for now , lets conclude the post .
I will cover the details in the coming post.



Comments