Subject Details
Dept     : ECE
Sem      : 5
Regul    : 2019
Faculty : A.Sakira Parveen
phone  : NIL
E-mail  : sakiraparveen.a.ece@snsct.org
540
Page views
31
Files
3
Videos
1
R.Links

Icon
Syllabus

UNIT
1
FUNDAMENTALS OF MACHINE LEARNING

Definition of learning systems-Goals and applications of machine learning- Types of Machine Learning- - Machine Learning Process-Terminology-Weight Space-The Curse of Dimensionality- Testing Machine Learning Algorithms.

UNIT
2
SUPERVISED LEARNING

Regression: Linear Regression –Parametric Models- Multivariate Regression. Classification: Bayesian Decision Theory-parametric and non-parametric methods- Multivariate Classification - Logistic Regression- K-Nearest Neighbor classifier. Decision Tree based methods for classification and Regression- Ensemble methods.

UNIT
3
UNSUPERVISED LEARNING

Introduction-Clustering-K-means clustering, EM algorithm, Hierarchical Clustering- Principal Component Analysis- Probabilistic PCA.

UNIT
4
NEURONS & NEURAL NETWORKS

The Brain and The Neuron-Neural Networks-Perceptron-Training the perceptron -Perceptron Learning Algorithm- Multilayer Perceptron- Back Propagation -Dimensionality Reduction.

UNIT
5
DEEP LEARNING

Convolutional Networks, Recurrent Neural Networks, Bidirectional RNNs, Deep Recurrent Networks, Recursive Neural Networks, Applications – Speech Recognition.

Reference Book:

1. Stephen Marshland, “Machine Learning: An Algorithmic Perspective”, Chapman & Hall/CRC 2009. 2. Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar, “Foundations of Machine Learning”, MIT Press (MA) 2012.

Text Book:

1. Ethem Alpaydin, “Introduction to Machine Learning”, 4th edition, MIT Press, March 2020. 2. Mitchell, Tom, “Machine Learning”, New York, McGraw-Hill, First Edition, 2013. 3. Ian Good Fellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press Book, 2016.