
This video will give students information about the outcomes of the course and the detail course structure which is composed of nine sections. They will get an idea about how to work on the course and what are the topics covered in this course
This video will tell learner how to link their .csv file which is stored in google drive with google colab IDE, a very useful video connecting data with IDE.
This Lecture is the first lecture of Section 1 of Basics of python module which give concepts of programming for students who are new to python programming. we have given basic introduction along with conditional statements in python using google colab in this lecture
This lecture is second in the series of basics of python, in this lecture concepts of loops are introduced to students along with examples.
This Lecture will give detail implementation of list in python
Important concepts of Dictionary is being introduced in this lecture along with tuples.
In this lecture students will get an idea about the functions in python along with practical exercise
Numpy is a very important package to understand carefully for building an efficient machine learning algorithm, so it is highly recommended to understand numpy in detail
Explore basic concepts of data frames with pandas, including column types (integer, object, float) and selecting columns with iloc and loc to print and inspect data for regression modeling.
Explore pandas basics for machine learning data analysis: compute max and mean, describe and view data shapes, filter with queries, and analyze categorical features with value_counts and crosstab.
The car_sample.csv file is provided to all of you have to build the model from scratch as being told in this lecture it consist of three parts, EDA, Data Cleaning , Model building and comparison with Random Forest Regressor
This lecture will describe how to build the first model using the concept of data exploration and data cleaning, after this we reduce the dimension of the data by using ffeature engineering and chosen best model to build one of the possible best model
Explore descriptive statistics as the foundation of machine learning, covering mean, variance, mode, and standard deviation, plus how normalization and z-scores situate data within the normal distribution.
Explore probability distributions, including Bernoulli, binomial, and Gaussian, and learn how PMF, PDF, and CDF describe discrete and continuous variables with mean mu and standard deviation sigma.
Master the machine learning pipeline from data and feature extraction through preprocessing and dimensionality reduction to training an ML model for classification, regression, clustering, and visualization.
Explore Bayesian learning and the Naive Bayes classifier, deriving Bayes rule and posterior probabilities using conditional independence. Apply to spam detection and cancer data with practical, from-scratch implementation.
Explore the naive Bayes classifier, its conditional independence of features x1 to xM, and how log likelihood and posterior maximization drive classification.
Learn how a Bayesian classifier trains feature distributions and multiplies their PDFs by class to classify data. Explore Bayesian networks for graphical probabilistic inference with variables like weather and rain.
Explore implementing a Gaussian naive Bayes classifier in Python from scratch, training feature distributions, standardizing data, and evaluating with a confusion matrix to achieve about 91 percent accuracy.
Explore a from-scratch practical Naïve Bayes classifier for spam detection, computing word-level probabilities from training data, building spam and ham distributions, and predicting messages.
Learn how regularization adds a penalty to the cost function to prevent overfitting by constraining weights. Explore ridge, lasso, and elastic net, and how lambda and cross validation set balance.
Explore regularization theory and practical implementation of ridge and lasso regression, using housing data to apply weight penalties with lambda and norm concepts to prevent overfitting.
Explore principal component analysis to reduce high-dimensional data by projecting onto orthogonal components that maximize variance. Learn how covariance, eigenvalues, and eigenvectors guide component selection and dimensionality reduction.
Demonstrate linear discriminant analysis for dimensionality reduction, maximizing class separation via within-class and between-class scatter, and projecting data onto discriminative axes for two-class and multi-class cases.
Implement linear and quadratic discriminant analysis to maximize between class separation, compute class means and covariances, reduce to two dimensions, and classify with train-test splits and confusion matrices.
Learn to build principal component analysis from scratch in Python by selecting eigenvectors with maximum variance, forming a covariance matrix, and projecting data for dimensionality reduction and classification.
Explore the k-nearest neighbors algorithm in Python, using Euclidean distance and majority voting to classify a test instance from nearby training samples.
Explain linear regression with a line of best fit, minimize squared error via gradient descent on beta0 and beta1, and introduce logistic regression with a sigmoid probability threshold for classification.
Implement linear regression from scratch using gradient descent to minimize mean squared error, updating weight and bias on the air purity dataset to learn the line of best fit.
Explore ordinary least squares and linear regression on synthetic data, using scatterplots, and assess significance with F statistics and p-values for the independent and dependent variables.
Learn multiple linear regression with multiple features and data. Use least squares to estimate coefficients, assess model fit with R-squared and significance tests, and apply to a trucking time example.
Explore the significance test in multiple linear regression by using the F test for overall and individual significance, with p-values, alpha, and diagnostics like heatmaps and variance inflation factor.
Learn to implement multiple linear regression with machine learning, build a model from a data frame, and assess multicollinearity using the variance inflation factor.
Maximum Likelihood Estimation is use to determine the pdf value of a random value, which means the probability of random variable to belong a particular class or distribution
Explore logistic regression for binary classification, using the sigmoid function to estimate loan and credit card approval probabilities and select significant features with chi-square testing.
in this lecture we will implement a logistic regression classifier, which is used to check whether the customers using the coupon or not and their dependency on card and amount expenditure
In this test cases we have used Loan prediction data set for training the model, along with it i have also provided a test case which you can use to predict model values.
The CHI square is used to predict the significance of independent variable with target variable both are categorical.
To check the over all significance we have used Variance Inflation Factor for checking importance of variable
In this lecture we perform various important task on the training data like handling missing values dividing data and follow divide and conquer approach, then we applied feature engineering on continuous data
This lecture is in continuation with the above lecture here we will see how to choose important categorical features from a pool of features
Explore four decision tree approaches, including ID3, C4.5, CART, and GUIDE, and learn how entropy and information gain select root and splits while pruning and Gini impurity aid CART.
Explore the basics of decision trees, including internal and leaf nodes, and learn how entropy and information gain guide splits, with C4.5 and ID3 considerations.
Explore how ID3 uses entropy and information gain to select the best attribute at each decision node, with concrete Gulf War data and continuous-split handling.
Investigate entropy and information gain in decision trees, and analyze overfitting, bias, and variance to understand model generalization and the role of pruning and regularization.
Learn practical implementation of the ID3 decision tree, handling nominal data with entropy and information gain, and understand its limitations such as no pruning and overfitting relative to C4.5.
Explore the C4.5 decision tree algorithm, its improvements over ID3, and how entropy and information gain guide categorical data splits in supervised learning.
learn to build a decision tree from scratch in python, using information gain and entropy to select the best attribute and iteratively split four-dimensional data.
This algorithm will discuss the cart algorithm implemented on a small data set to identify fruits
CHAID is a very important decision tree which is based on the concept of finding chi square to check the significance of independent variable with respect to dependent variable. The selection of the feature or attribute depend upon the highest chi square value.
Explore the implementation of CHAID using Python to build decision trees, using entropy, information gain, and gain ratio, and compare with C4.5 while analyzing accuracy.
Explore what a recommendation system is, its real-life applications, and three major approaches: content-based, collaborative filtering, and hybrid filtering, with examples like Netflix and Amazon.
Explore memory-based collaborative filtering and the matrix-based approach for movie recommendations. Build a user-item matrix and compute similarities, such as cosine similarity, to weight ratings and predict user ratings.
Explore matrix decomposition for collaborative filtering by factorizing the rating matrix into two components, enabling outer-product predictions with user and item features, via singular value decomposition and regularization.
Explore item-based collaborative filtering by measuring item similarity using user rating patterns, normalization by item averages, and predicting ratings with weighted similar items.
Explore content-based filtering for movie recommendations by merging genres and user comments, vectorizing text, and using SVD to build a compact similarity-based recommendation model.
Explore collaborative filtering for movie recommendations, contrasting it with content-based systems. Learn how user-based and item-based approaches use cosine similarity to predict ratings from sparse data and feedback.
In this lecture students will learn how to combine Content based rating and Item Based Collaborative rating.
Explore clustering methods for recommendation systems, using sentiment-based features, elbow method to choose cluster count, and unsupervised learning to reveal patterns in user ratings and item data.
Implement gradient descent to train a recommendation system with collaborative filtering. Minimize mean square error on predicted ratings and tune with learning rate using training and testing data.
Learn how support vector machines classify data with linear and nonlinear boundaries by maximizing the margin and using support vectors to define the separating plane.
Describe constrained optimization in support vector machines, maximizing margin with Lagrange multipliers, identifying support vectors via alpha, and applying kernels for non-linear classification.
Explore the dual formulation of support vector machines, showing how maximizing the margin via support vectors leads to better generalization, with kernel mappings to higher dimensions.
The concept of soft margin classifier in SVM is explained in detail in this lecture along with the concept of dual form of Lagrange expression which has some condition which are very important in optimizing the solutions
After completing this lecture students will understand the concept of support vector machine more clearly, they also came to know how to maximize the margin separation between two classes
Explore nonlinear transformation in svm by mapping data into higher-dimensional z-space using kernels. Learn polynomial and radial basis function kernels and how slack variables enable soft-margin classification.
Learn to implement linear and non-linear support vector classifiers in python, focusing on data scaling, feature engineering, and kernel trick with polynomial kernels to improve accuracy.
Explore the implementation of support vector regression, focusing on fitting a regression line with a margin and an error tube, using kernels like a second-degree polynomial.
Explains one-vs-one and one-vs-all multiclass SVM strategies, with nonlinear separation via mapping to higher dimensions and the creation of multiple hyperplanes for each class pair.
Demonstrate a practical case study of implementing a support vector classifier, covering margins and hyperplanes, explore linear, polynomial, and radial basis function kernels, and assess accuracy on iris data.
Explore implementing a support vector regressor on the Boston housing data to predict prices, using mean squared error and absolute error, and discuss the role of support vectors and gamma.
Explore how TensorFlow builds neural and deep neural networks via a graph model with parallel execution, using the high-level API and layers like Sequential and Dense with sigmoid activations.
Explore data representation in tensors, from zero dimensional scalars to five dimensional video tensors, detailing vectors, matrices, color channels (bgr), and image shapes for machine learning.
Discover how artificial neural networks mimic brain processing with data vectors, weights (synaptic connections), and activation functions, learning to minimize error via machine learning.
Explore the perceptron by computing z as w transpose x plus bias, applying the Heaviside step activation to output binary 0/1 values, and outlining weight updates with a learning rate.
Implement a practical perceptron classifier by wiring input features, weights, and bias into a simple neuron, and classify samples into two classes using Python.
This lecture will give students information about gradient descent algorithm which is a very important mechanism for parameter tuning.
compare gradient descent with stochastic gradient descent and mini-batch approaches, showing how per-sample weight updates offer fast convergence while risking missing the global minimum and overfitting.
Divide data into small batches, compute mean squared error per batch, and update weights after each batch; mini-batch gradient descent sits between stochastic and full-batch methods in neural networks.
Build and evaluate a mlp on the amnesty handwritten digits dataset (28×28, 60k train, 10k test) using a 2-layer sequential model with 128 hidden units, ReLU, dropout, and softmax cross-entropy.
Master the back propagation algorithm in neural networks by learning how to propagate error backward, update synaptic weights and biases, and iterate through epochs to minimize the error.
Learn batch normalization for neural networks, applying normalization to input and feature vectors before activation, using gamma and beta with epsilon, computed across mini-batches to stabilize training and accelerate learning.
Learn to build a TensorFlow classifier for fashion mnist’s 28x28 grayscale images across 10 categories, including data preprocessing, training with categorical cross-entropy, and evaluating accuracy.
Train a TensorFlow model on Boston housing data to predict housing prices using k-fold validation. Build a two-hidden-layer network with 64 neurons, normalize with Z-score, and evaluate mean absolute error.
Explore convolutional neural networks by building a sequential network with 28x28 grayscale inputs, 3x3 filters, max pooling, flattening, and a dense layer, trained with Adam and categorical cross-entropy.
Explore OpenCV basics for computer vision in Google Colab, loading images, performing color conversions (bgr to rgb), and applying translation, rotation, resizing, cropping, flipping, and dilation or erosion.
Explore unsupervised learning and clustering, covering k-means partitioning, hierarchical clustering, Gaussian mixture models, and DBSCAN, with hands-on Python implementations and result analysis to guide algorithm choice.
Explore k-means clustering by updating centroids and assigning points to nearest centers, observing convergence. Note limitations with high-dimensional data and outliers, and consider fuzzy c-means or hierarchical approaches.
This lecture demonstrates the k means algorithm with two clusters, computing distances to cluster centers, assigning each point to the nearest center, and updating cluster means for propagation.
Demonstrate k-means clustering in python using wholesale data to form clusters and improve classification, then assess quality with elbow method and silhouette coefficient, applying scaling and variance inflation factor checks.
Learn to implement and interpret the silhouette coefficient to evaluate cluster quality, comparing distances within and between clusters, and apply the elbow method to create and test cluster configurations.
Apply bottom-up hierarchical agglomerative clustering, building successively larger clusters from Euclidean distances and dissimilarity matrices, and compare linkage types such as single linkage to reveal evolving cluster structures.
Learn to implement hierarchical agglomerative clustering with PCA to reduce high-dimensional data to two components, explore threshold-based cluster counts, and assess cluster quality with compactness and the silhouette coefficient.
Explore the fuzzy c-means algorithm by initializing memberships, computing centroids, and updating cluster memberships using inverse distance weights, enabling probabilistic boundaries across two clusters.
Practical implementation of FCM algorithm using Python
Learn how mean shift clustering forms clusters by iteratively shifting data toward high-density regions within a radius, converging as centers stabilize and the number of clusters emerges.
Learn dbscan density based clustering, which uses core points, an epsilon radius, and a minimum point count to form clusters while identifying outliers without predefining cluster numbers.
Explore independent Gaussian mixtures for multivariate data, derive class-conditional probabilities with the multivariate Gaussian distribution, and apply Bayesian classifiers for classification and regression.
This lecture gives a practical aspect of how clusters are viewed as Gaussian Normal Distributions. In this lecture we try to separate overlapping clusters
Explore how random forest uses bootstrap samples and random feature subsets to build multiple decision trees, vote for classification, and handle missing data with proximity matrices on breast cancer data.
The Concepts of Voting classifier both soft voting using predict_proba() method and hard voting classifier have been explained in this lecture using data. The bagging classifier is also being implemented to give students an idea about both types of classifiers
The random forest is an ensemble of lot of decision trees breast cancer data set has been used to implement this classifier
Compare random forest regression with linear regression, explain the ensemble of decision trees, build a random forest model, and evaluate predictive accuracy against linear regression.
Explore Ada Boost implementation on breast cancer data, including preprocessing, normalization, stratified train-test split, and comparing boosting with random forest and logistic regression performance.
This lecture deals with building a Gradient Boosting Regression Tree, a very powerful model which work on the base estimator which is Decision Tree Regressor. Then we have introduced stage predict() method which work on the concept of early stopping
This course of "A Comprehensive Course on Machine Learning using python" is a very comprehensive and unique course in itself. Machine Learning is a revolution now days but we cannot master machine learning without getting the mathematical insight, and this course is designed for the same. Our course starts from very basic to advance concepts of machine learning. We have divided the course into different modules which start from the introduction of python its programming basic and important programming constructs which are extensively used in ML programming.
The mathematics involved in Machine learning is normally being not discussed and being left out in , but in our course we have put lot of emphasis in mathematical formulation of algorithms used in ML. We have also designed modules of pandas, sklearn, scipy, seaborn and matplotlib for gearing the students with all important tools which are needed in dealing with data and building the model. The machine learning module focuses on the mathematical derivation on white board through video lectures because we believe that white box view of every concept is very important for becoming an efficient ML expert.
In Machine Learning the cost estimation function also called loss functions are very important to understand and in our course we have explained Cross Categorical Entropy, Sparse Categorical Cross Entropy, and other important cost functions using TensorFlow.
Concepts like gradient descent algorithm, Restricted Boltzmann Algorithm, Perceptron, Multiple Layer Perceptron, Support Vector Machine, Radial Basis Function , Naïve Bayes Classifier, Ensemble Methods, recommendation system and many more are being implemented with examples using Google Colab.
Further I wish best of luck to learners for their sincere efforts in advance…
Use of various components of statistics in analyzing data
Graphical representation of data to get deep insight of the patterns
Mathematical analysis of algorithms to remove the black box view
Practical implementation of all important ML Algorithms
Building various models from scratch using advance algorithms
Understanding the use of ML in research
Quiz at the end of each section