Salient Features of NN

By Mayuri Bapat
Learning
 Main property of ANN is its learning
capability. There are two types of learning
 Parameter Learning :- It updates connecting
weights in neural nets.
 Structure learning :- It focusses on change in
neural network.
 Generally, it is classified into
 Supervised Learning
 Unsupervised Learning
 Reinforcement Learning
IC: Google
Supervised Learning
 Supervised learning, as the name indicates, has the
presence of a supervisor as a teacher. Basically,
supervised learning is when we teach or train the
machine using data that is well labelled. 
 Supervised learning is a machine learning approach
that’s defined by its use of labelled datasets.
 These datasets are designed to train or “supervise”
algorithms into classifying data or predicting
outcomes accurately. 
 Using labelled inputs and outputs, the model can
measure its accuracy and learn over time.
There are two main areas where supervised learning
is useful: classification problems and regression
problems
 Classification problems use an algorithm to accurately assign test data into specific
categories, such as separating apples from oranges. Or, in the real world, supervised
learning algorithms can be used to classify spam in a separate folder from your
inbox. Linear classifiers, support vector machines, decision trees and random forest
 are all common types of classification algorithms.
 Regression is another type of supervised learning method that uses an algorithm to
understand the relationship between dependent and independent variables.
Regression models are helpful for predicting numerical values based on different data
points, such as sales revenue projections for a given business. Some popular
regression algorithms are linear regression, logistic regression and polynomial
regression.
For instance, suppose you are given a basket filled with
different kinds of fruits. Now the first step is to train the
machine with all different fruits one by one like this: 

IC: Google
 If the shape of the object is rounded and has a depression at the top, is red in color, then it will be labelled as
–Apple.
 If the shape of the object is a long curving cylinder having Green-Yellow color, then it will be labelled as –
Banana. 
 
 Now suppose after training the data, you have given a new separate fruit, say Banana from the basket, and
asked to identify it. 
 

Since the machine has already learned the things from previous data and this time have to use it wisely. It
will first classify the fruit with its shape and color and would confirm the fruit name as BANANA and
put it in the Banana category. Thus the machine learns the things from training data(basket containing
fruits) and then applies the knowledge to test data(new fruit). 
 Supervised learning deals with or learns with “labelled” data. This implies that some
data is already tagged with the correct answer.
 Types:-
 Regression
 Logistic Regression
 Classification
 Naive Bayes Classifiers
 K-NN (k nearest neighbours)
 Decision Trees
 Support Vector Machine
Advantages:-

 Supervised learning allows collecting data and produces data output from previous
experiences.
 Helps to optimize performance criteria with the help of experience.
 Supervised machine learning helps to solve various types of real-world computation
problems.
Disadvantages:-

 Classifying big data can be challenging.

 Training for supervised learning needs a lot of computation time. So,
it requires a lot of time.
Unsupervised learning 

 Unsupervised learning uses machine learning algorithms to analyse and cluster

unlabelled data sets. These algorithms discover hidden patterns in data without
the need for human intervention (hence, they are “unsupervised”).
 Unsupervised learning models are used for three main tasks: clustering,
association and dimensionality reduction:
 Clustering is a data mining technique for grouping unlabelled data based on
their similarities or differences. For example, K-means clustering algorithms
assign similar data points into groups, where the K value represents the size of
the grouping and granularity. This technique is helpful for market segmentation,
image compression, etc.
Actual
Input X ANN W Output
 Y
 Unlike supervised learning, no teacher is provided- that means no training will be
given to the machine. Therefore, the machine is restricted to find the hidden
structure in unlabelled data by itself. For instance, suppose it is given an image
having both dogs and cats which it has never seen.
 Thus, the machine has no idea about the features of dogs and cats so we can’t
categorize it as ‘dogs and cats ‘. But it can categorize them according to their
similarities, patterns, and differences, i.e., we can easily categorize the above picture
into two parts. The first may contain all pics having dogs in it and the second part
may contain all pics having cats in it. Here you didn’t learn anything before, which
means no training data or examples. 
  It allows the model to work on its own to discover patterns and information that was
previously undetected. It mainly deals with unlabelled data.
 Unsupervised learning is classified into two categories of algorithms: 
 
 Clustering: A clustering problem is where you want to discover the inherent
groupings in the data, such as grouping customers by purchasing behaviour.
 Association: An association rule learning problem is where you want to discover
rules that describe large portions of your data, such as people that buy X also tend to
buy Y.
 Types of Unsupervised Learning:-
 Clustering
 Exclusive (partitioning)
 Agglomerative
 Overlapping
 Probabilistic
 Clustering Types:-
 Hierarchical clustering
 K-means clustering
 Principal Component Analysis
 Singular Value Decomposition
 Independent Component Analysis
Supervised Learning Unsupervised Learning

Supervised learning algorithms are trained using labeled data. Unsupervised learning algorithms are trained using unlabeled data.

Supervised learning model takes direct feedback to check if it is predicting Unsupervised learning model does not take any feedback.
correct output or not.

Supervised learning model predicts the output. Unsupervised learning model finds the hidden patterns in data.

In supervised learning, input data is provided to the model along with the In unsupervised learning, only input data is provided to the model.
output.
The goal of supervised learning is to train the model so that it can predict the The goal of unsupervised learning is to find the hidden patterns and useful
output when it is given new data. insights from the unknown dataset.

Supervised learning needs supervision to train the model. Unsupervised learning does not need any supervision to train the model.

Supervised learning can be categorized Unsupervised Learning can be classified

in Classification and Regression problems. in Clustering and Associations problems.

Supervised learning can be used for those cases where we know the input as Unsupervised learning can be used for those cases where we have only input
well as corresponding outputs. data and no corresponding output data.

Supervised learning model produces an accurate result. Unsupervised learning model may give less accurate result as compared to
supervised learning.

Supervised learning is not close to true Artificial intelligence as in this, we Unsupervised learning is closer to the true Artificial Intelligence as it learns
first train the model for each data, and then only it can predict the correct similarly as a child learns daily routine things by his experiences.
output.

It includes various algorithms such as Linear Regression, Logistic It includes various algorithms such as Clustering, KNN, and Apriori
Regression, Support Vector Machine, Multi-class Classification, Decision algorithm.
tree, Bayesian Logic, etc.
Reinforcement Learning
  This learning process is like supervised learning. In case of
supervised learning target output values are known for each
input pattern. But in some cases, less information might be
available. 

 Exa, the network might be told that its actual output is only
"50% correct" Or So. Thus, here only critic information is
available not the exact information. The learning based on this
critic information is called reinforcement learning & feedback
sent is called reinforcement signal. 
Input
Signal Actual
X Neural Network Output

Error Reinforcement
Error Signal Generator  Signal
Signal

Fig.: Reinforcement Learning

component

 Input layer
 Hidden layer
 Output layer
 Weights
 Bias
 How many types of Artificial Neural Networks?
1
2
3
4

A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant
of proportionality being equal to 2. The inputs are 4, 10, 5 and 20 respectively. What will
be the output? Answer is =119*2=238
Thank you.