https://meet.google.com/pmp-dybr-mzb
Basics of Machine Learning: Introduction to machine learning, artificial intelligence and deep learning. Learning algorithms - over fitting and under fitting, hyperparameters and validation sets, estimators, bias and variance, Maximum Likelihood Estimation. Machine learning process flow- define problem, objective, data acquisition and preprocessing, feature engineering, model building and validation.
Supervised and Unsupervised Learning: Supervised Learning- Basic principles of linear regression, logistic regression. Classification-Supervised algorithms-Decision trees, k-Nearest Neighbour, Naïve Bayes, support vector machines, ensemble learning techniques. Unsupervised Learning- Basic principles of clustering, clustering algorithms-hierarchical algorithms-agglomerative, divisive algorithms. Partitioning algorithms- k-means, k medoids algorithms, density based algorithms.
Semi-supervised and Reinforcement Learning: Semi-supervised learning – Types of semi-supervised learning- Self learning, graph based SSL-label propagation. Reinforcement Learning-Taxonomy, Reinforcement Learning Algorithms-Value based, Policy based and model based algorithms. Characteristics and types of reinforcement learning. Reinforcement learning models- Markov decision process, Q-learning.
Artificial Neural Networks and Deep Learning: Artificial neural networks- Basic principles of Back propagation, Gradient Descent, Training Neural Network, Initialisation and activation functions. Deep learning principles and architectures-Dropout, Batch normalisation, Ensemble learning, Data augmentation, Transfer learning, Convolutional Neural Networks, Recurrent Neural Networks, LSTM, Data augmentation-GAN.
Applications of Machine Learning: Machine learning applications for prediction-weather, sales of a store, eligibility of loan. Medical diagnoses, Financial industry and trading, image classification, recognition and segmentation, speech recognition, automatic language translation and auto corrections, recommendation engines.
Flach, Peter. Machine learning: the art and science of algorithms that make sense of data. Cambridge university press, 2012.
Gopal, Madan. Applied machine learning. McGraw-Hill Education, 2019.
Haykin, Simon. Neural networks and learning machines, 3/E. Pearson Education India, 2009.
Bishop, Christopher M., and Nasser M. Nasrabadi. Pattern recognition and machine learning. Vol. 4. No. 4. New York: springer, 2006.
Continuous Internal Evaluation: 40 marks
Quiz 1: 2.5 marks
Quiz 2: 2.5 marks
Seminar: 5 marks
Course Project: 20 marks
Implementation: 10 marks
Results: 5 marks
Presentation and Report: 5 marks
Internal Examination: 10 marks
End-semester Examination: 60 marks
As part of the course project, the creditors of the course have to implement a machine learning algorithm on a publicly available datasets. M.Tech. scholars are encouraged to choose a project from the list given below whereas the Ph.D. scholars can choose a project from outside the list after consulting their research supervisor(s). In any case, the creditors have to get the project topics approved by the course instructor before the 5th lecture.
Suggested Project Topics:
Classification of phonological categories in imagined speech Reference Paper Dataset
Classification of motor imagery from EEG Reference Paper Dataset
Classification of imagined words from EEG Reference Paper Dataset
Modeling wine preferences by data mining from physicochemical properties Reference Paper Dataset
Breast cancer histopathological image classification using AlexNet Reference Paper Dataset
Music genre classification with convolutional neural networks Reference Paper Dataset
Sentiment classification system of twitter data for US airline service analysis Reference Paper Dataset
Classification of emotions from EEG Reference Paper Dataset
Online handwriting recognition system for Tamil Reference Paper Dataset
Real-time credit card fraud detection Reference Paper Dataset
Speech emotion recognition Reference Paper Dataset
Topic allotment:
Akhil B S: Modeling wine preferences by data mining from physicochemical properties
ALKA GILBERT: Music genre classification with convolutional neural networks
Archana M: Breast cancer histopathological image classification using AlexNet
DEVIKA K P: Classification of emotions from EEG
Gopika A K: Classification of motor imagery from EEG
JINCY M S: Sentiment classification system of twitter data for US airline service analysis
Kailas Nath V D: Classification of phonological categories in imagined speech
KRISHNA RAJEEV: Classification of imagined words from EEG
NISHANA YASMIN: Classification of motor imagery from EEG
SAJLA KM: Determining chess game state from image
Veena P: Online handwriting recognition system for Tamil
Sangeetha Gopan: Prediction of the capacitance of activated carbon supercapacitor electrodes
Jesna K A: Sleep apnea detection from ECG
Anju J.S.: Facial emotion recognition using CNN
Mala J.B: Sentiment Analysis of IMBD data
Course File_221TEC004: Topics in Machine Learning Attendance
Seminar Topics Folder for Uploading Seminar Presentations