M.Tech in Artificial Intelligence

Python is one of the most popular and effective programming languages employed in Artificial Intelligence. Python is believed as a simple yet high-level general-purpose programming language. The first module of the Artificial Intelligence Course will let you get comfortable with the Python programming language.
Below are the various concepts of Python for Data Science you would master in this module.

In this sub module, you would first learn the basics that assist you master Python.

A data structure is a data management component that facilitates efficient access and modification. In this sub module, you will learn about Data Structures & handling.

A function is a group of statements that receive inputs, perform some specific computation and provide output. In this sub module, you will learn about Functions.

Numpy is a Python library used for Python programming. Numpy affords a simple yet powerful data structure.In this sub module, you will learn about Numpy.

Pandas are employed to perform an effective data analysis. Pandas execute several data manipulation operations such as merging, reshaping, selecting, cleaning, and more. In this sub module, you will learn about Pandas.

SciPy is another free and open-source Python library utilised for performing scientific computing and technical computing.In this sub module, you will learn about Scipy.

Scikit-learn is a free machine learning library employed for executing the Python programming language. In this sub module, you will learn about Scikit-learn.

Statistics is an essential aspect of Artificial Intelligence. In this module, you will learn about several statistical concepts and procedures employed in Artificial Intelligence for Decision Making.
In this module of the AIML course, you will learn about the various concepts of Statistical Methods For Decision Making.

Descriptive statistics is the method of analyzing the given data. A descriptive statistic is a core statistic that quantitatively details or compiles the traits from a set of information. Inferential statistics assist to suggest solutions for a situation or phenomenon. It lets you draw effective conclusions based on extrapolations.In this sub module, you will learn about Descriptive and Inferential Statistics.

A probability distribution is a mathematical function that gives the probabilities of occurrence of many likely possible outcomes for a given analysis. In this sub module, you will learn about Probability & Distributions.

Hypothesis testing is a statistical test where we test an assumption considering a group parameter. This is used to estimate the plausibility of a hypothesis by using sample data. In this sub module, you will learn about Hypothesis Testing.

The chi-square is employed to examine whether the distribution of classes fits the distribution model. ANOVA is used to study whether differences in means within the samples are notable or not.In this sub module, you will learn about Anova and ChiSquare.

Dispersion is a statistical term that illustrates the dimension of the distribution of values assumed for a specific variable. Dispersion can be measured by various statistics, such as range, variance, and standard deviation. In this sub module, you will learn about several measures of Dispersion.

Simulation is a statistical method used to evaluate the performance of a method, especially when there is a lack of theoretical knowledge. In this sub module, you will learn about statistical simulation techniques.

Mathematics is one of the most crucial aspects of Artificial Intelligence and Machine Learning. In this module of the Artificial Intelligence course, you will learn about several concepts of Mathematics employed in AIML.
Below are the various concepts of Mathematical Foundation you would master in this module of the M.Tech in Artificial Intelligence course.

Linear Algebra is a mathematical application that is greatly useful in data science and machine learning. Linear algebra is applied in the execution of data preprocessing, data transformation, and model evaluation. In this sub module, you will learn about Linear Algebra for Data Science.

Vectors and Matrices are vividly used in Artificial Intelligence to work on data. In this sub module, you will learn about

In this sub module, you will learn about several mathematical functions and derivatives that boost your expertise to work on AIML models.

Eigenvalues are the constants that enhance or reduce the Eigenvectors along with their extent when transformed linearly. In this sub module, you will learn about Eigen Decomposition - PCA

The singular value decomposition refers to the factorization of a real or complex matrix. In this sub module, you will learn about Singular Value Decomposition

Optimisation functions are used to calculate the gradient which is the partial derivative of the loss function. In this sub module, you will learn about Optimisation and Loss functions.

Data Analysis and Visualization are the two important concepts of Artificial Intelligence and Machine Learning.
Below are the various concepts of Data Analysis and Visualization you would master in this module of the M.tech in Artificial Intelligence and Machine Learning course.

In this sub module, you will learn the tools and techniques employed to understand the given data.

Descriptive analysis in AIML is used to define the basic characteristics of the data in a study. In this sub module, you will learn about Descriptive Analysis.

Bivariate analysis is one of the simplest methods of statistical analysis, applied to learn if there is a correlation between two sets of values. In this sub module, you will learn about Bivariate Analysis

Multivariate analysis refers to the statistical analysis of data gathered through multiple dependent variables. In this sub module, you will learn about Multivariate Analysis

Data Preprocessing is a procedure applied to transform the raw data into a clean data set. In this sub module, you will learn about Data Pre-processing

Data visualization is defined as a graphical representation of the derived data using several visual elements like charts, graphs, and maps. In this sub module, you will learn about several Data Visualization tools and techniques.

Machine Learning is an important subset of Artificial Intelligence. The module of Machine learning will teach us Machine Learning techniques and all the popularly used in Classical ML algorithms that fall in each of the categories.
Below are the various concepts of Machine Learning you would master in this module of the Artificial Intelligence training.

Regression is a supervised learning technique that assists in finding the relationship between variables and facilitates us to predict the continuous output variable based on one or more predictor variables. In this sub module, you will learn about Supervised Regression.

• Exploratory data analysis

As the name suggests, The concept of Exploratory Data Analysis or EDA revolves around exploring data. Data Exploration is of three types. They are Data Summarization, Data Visualization, and Data Normalization. In this sub-module, you would learn several EDA techniques. In this sub module, you will learn about Exploratory Data Analysis.

• Linear Regression (LR)

Linear Regression is applied to forecast the outcome that is continuous and has a constant slope within a continuous range. In this sub module, you would learn the several techniques of Linear Regression. In this sub module, you will learn about Linear Regression.

• Statistical Significance of LR

The likelihood ratio refers to the probability of accurately predicting disease in ratio to the probability of inaccurately predicting disease. In this sub module, you will learn about Statistical Significance of LR.

• Feature engineering

Feature engineering refers to the process of applying domain knowledge to extract traits such as characteristics, properties, attributes and more from the given raw data. In this sub module, you will learn about Feature Engineering.

• Regularization Techniques

Regularization is a procedure that makes inadequate adjustments to the learning algorithm such that the given model renders better results.In this sub module, you will learn about Regularization Techniques.

• Model deployment

Model deployment is an engineering task employed for putting a Machine Learning model to use. In this sub module, you will learn about Model deployment.

Supervised classification allows the user to select sample pixels in an image that are illustrative of specific classes and then direct the image processing software to use these. In this sub module, you will learn about Supervised Classification.

• Logistic Regression

In statistics, the logistic regression model is used to define the probability of a definite class or event existing such as true/false. In this sub module, you will learn about Logistic Regression.

• K-Nearest Neighbours

In this sub module, you will learn about K-Nearest Neighbours.

• Decision Trees

Decision trees are used to investigate the models as they aid effective decision-making. A decision tree is a support tool that uses a tree-like pattern of decisions and possible consequences, including accident event outcomes, resource costs, and service. In this submodule, you will also learn about Decision Trees.

• Ensemble Techniques

Ensemble techniques offer multiple models and then merge them to produce improved results. Ensemble techniques usually deliver the most reliable solutions than within a single model. In this submodule, you will also learn about Ensemble Techniques.

• Naive Bayes

Naive Bayes is a classification technique executed based on Bayes' Theorem which uses an assumption of independence among predictors. In this submodule, you will also learn the several techniques of Naive Bayes

• Model Improvement

In this sub module, you will learn about the several techniques employed in Model Improvement.

An unsupervised model is a type of machine learning model in which the model is not given any pre-assigned tags for the training data. In this sub module, you will learn about Unsupervised Model.

• Clustering Techniques

Clustering is an important technique of Machine learning. It is the task of splitting the number of data points into several groups. In this submodule, you will learn several techniques of Clustering.

• K-means algorithm

K-Means Clustering is an Unsupervised Learning algorithm, which gathers the unlabeled dataset into different clusters. In this sub module, you will learn about K-means algorithm

• Hierarchical Clustering

Hierarchical clustering is an algorithm that gathers similar elements into groups called clusters. In this sub module, you will learn about Hierarchical Clustering

• Dimensionality Reduction

Dimensionality reduction refers to the tools and techniques applied for transformation of a given data from a high-dimensional space into a low-dimensional space. In this sub module, you will learn about Dimensionality Reduction.

• Recommender system

Recommender system is an important application of AIML in which the systems try to recommend products and services to the user based on many different factors such as past purchases, search history and more. In this sub module, you will learn about the Recommender System.

• Market Basket Analysis

Market basket analysis is a data mining technique used to understand a customer's behaviour and boost sales. In this sub module, you will learn about Market Basket Analysis.

Time series forecasting can be defined as the set of observations on the values that a variable takes at different times. Time Series Forecasting is employed in statistics, econometrics, mathematical finance, weather forecasting, earthquake prediction and many more.
Below are the various concepts of Time Series Forecasting you would master in this module of the Masters in Artificial Intelligence course.

Decomposition affords another means to factorize a time series into singular vectors and singular values. In this sub module, you will learn about techniques involved in Decomposition.

Moving average is a smoothing technique used in time series analysis and forecasting. It refers to the process of designing a new series in which the values are comprised of the average of raw observations in the primary time series. In this sub module, you will learn about Moving Average.

In this sub module, you will learn more about Time Series Forecasting.

Autocorrelation is a measure of the association between the delayed values of a time series. In this sub module, you will learn about Auto Correlation.

ARIMA stands for AutoRegressive Integrated Moving Average. It is a generalization of a more simplistic AutoRegressive Moving Average and scores the notion of integration. In this sub module, you will learn about ARIMA.

SARIMA stands for seasonal autoregressive integrated moving average models. These models are applied for modeling seasonal time series. In SARIMA, the mean and other statistics for a given season are not stable across the years. In this sub module, you will learn about SARIMA.

Deep learning is a subset of machine learning that concentrates on imitating the way the human brain enacts to obtain certain types of knowledge.
Below are the various concepts of Deep Learning you would master in this module of the AIML course.

A neural network is a series of algorithms that tries to identify underlying correlations in a set of data through a process that imitates the way the human brain operates. In this sub module, you will learn about Neural Networks.

Keras is a neural network library and TensorFlow is the open-source library for executing several tasks in machine learning technology. In this sub module, you will learn about Tensorflow and Keras.

CNN stands for Convolutional Neural Network which is an approach to artificial neural networks. CNN is broadly applied in image recognition and classification. In this sub module, you will learn about CNN and its applications.

Transfer learning is a machine learning technique in which a model built for the execution of one task is reused as the opening point for a model on a second task. In this sub module, you will learn about Transfer learning and Applications

Object detection refers to the capability of machine systems to discover objects in a given image and classify each object. In this sub module, you will learn about Object detection.

Natural language processing is a process where human language is segregated into several fragments so that the actual context of the words in a given search can be analyzed and understood. In this sub module, you will learn about Natural Language Processing

• Text Analytics - Basics

Text Analytics is the method of deriving insights out of written communication.In this sub module, you will learn about Text Analytics - Basics.

• Document summarization and classification

Document Summarization refers to the task of revising a document into a more compressed fashion while still retaining its content. In this sub module, you will learn about the techniques involved in Document Summarization and classification.

• Web Scraping

Web scraping is the method of applying bots to derive content and data from a specific website. In this sub module, you will learn about the techniques of Web Scraping.

• Sequential Modelling

Sequence Modelling is the strength of a computer program to design, evaluate, make predictions about or produce any type of sequential data, such as audio, text etc. In this sub module, you will learn about Sequential Modelling.

• Transformers

A transformer is a deep learning application that adopts the mechanism of attention, differentially considering the importance of each element of the input data. In this sub module, you will learn about Transformers.

Computer vision is an application of artificial intelligence (AI) that facilitates machines to derive meaningful insights from digital images, videos and other visual inputs. In this sub module, you will learn about Computer Vision.

• Image formation and preprocessing

Image preprocessing refers to the set of steps implemented to format images before they are used by model training and inference. In this sub module, you will learn about Image formation and preprocessing.

• Noise Filtering

Noise filtering is a set of techniques employed to eliminate the noise contained with the data acquired. In this sub module, you will learn about Noise Filtering.

• Image Segmentation

Image segmentation is a major component of image processing that concentrates on partitioning an image into different parts considering their features and properties. In this sub module, you will learn about Image Segmentation.

• Feature Extraction

Feature extraction refers to the process of dimensionality trimming by which a primary set of raw data is reduced to more flexible groups for processing. In this sub module, you will learn about Deep Learning models for future extraction.

• Image classification

Image classification refers to the process of classifying and labelling groups of pixels or vectors within an image based on definite rules. In this sub module, you will learn image classification.

• Deep Learning models for image processing

Deep learning models are being applied in Google search and image search. Deep Learning models enable you to image-search using the keyword terms. In this sub module, you will learn about Deep Learning models for image processing.

Below are the various concepts of Advanced Deep Learning you would master in this module of the Artificial Intelligence course.

Object detection defines the ability of computer and software systems to discover objects in an image and identify them.In this sub module, you will learn about Object Detection.

A Siamese neural network is an artificial neural network that practices the same weights while operating in tandem on two distinct input vectors to measure relative output vectors. In this sub module, you will learn about Siamese Networks

Object Segmentation refers to the process of classifying each pixel value of an image to a distinct class. In this sub module, you will learn about Object Segmentation.

GAN stands for Generative adversarial networks which are algorithmic architectures that utilise two neural networks, pitting one against the other to produce new, artificial data instances that can succeed for real data. In this sub module, you will learn about GANs.

Autoencoder is a kind of neural network that is applied to acquire a compressed representation of raw data. In this sub module, you will learn about Auto Encoder.

Learners will be offered five enthusiastic specializations to choose from.

Operations research is described as the scientific process of transforming data into insights for deriving better decisions.

Industrial safety refers to the administration of all operations and functions within an enterprise to secure its employees and assets by reducing hazards, identifying risks, and more.

Entrepreneurship is the thought of building and maintaining a business enterprise to obtain profit.Intellectual Property rights (IPR) aid innovative entrepreneurs to protect their inventions.

Business analysis refers to the practice of identifying business needs and defining the most meaningful solutions to complex business problems.

Professional ethics are principles that direct the actions of a person or group in an organisation.