Artificial Intelligence / Machine Learning – HDSOFT Technologies

Artificial Intelligence /Machine Learning Course – Get Future Ready with AI Skills

Overview

Syllabus

Overview

Our AI course offers a comprehensive, hands-on learning experience designed to equip you with real-world skills in Artificial Intelligence and Machine Learning. With a learner-centric approach, this 8-week course combines in-person and online interactive sessions, real-world projects, and expert mentorship to ensure you’re job-ready. Gain practical experience with Python, AI/ML algorithms, and cutting-edge tools to excel in the industry.

Syllabus

Week 1

In Person				Virtual
	Day 1	Day 2	Day 3	Sunday (Day 4)
	Assignment review (Day 2 onwards)			Assignment review
Introduction	Essentials of Python Programming	Revisit day 1 topics and their implementation	Introduction to Statistical Analysis packages – Statsmodel and SciPy	Arithmetic operations and File handling
Assisted practice	Seeting up Jupyter Notebook	Working with CSV file	Scikit-learn	Conditional logic, Indexing and slicing
	Python functions	Working with Lambda function	Implement Statsmodel	File handling, Introduction to linear algebra
	Working with Python types	Understanding List comprehension	Implement Scipy	Scalars and vectors, dot product of vectors, norm of a vector
	Working with Python sequences	Python and data analysis	Common mathematical and statistical functions in NumPy	Matrix operations, transpose of a matrix, determinant of a matrix
	Python Strings	Understanding python packages available for data science	Evaluate webscaping techniques using BeatifulSoup	Eigenvalues and Eigenvectors
	Exploring Python Date and Time	Pandas, NumPy [Data manipulation]. Array shapes and axes in NumPy	Evaluate web scraping techniques using Scrapy	Break
	Python map() function and its usage	Matplotlib, seaborn, Plotly [Data visualization]		Statistics fundamentals, Data categorization and types
Assignment Discussion	Implement all the above functionality in a python program	Research on BeautifulSoup and scrapy. Exercise 1 – implementation of BeautifulSoap and Scrapy	Exercise 2 – Work on a sample dataset to create a dashboard using data visualization modules	Self study on basic statistical concepts to be covered in upcoming classes

Week 2

In Person				Virtual
	Day 5	Day 6	Day 7	Sunday (Day 8)
	Assignment review			Assignment review
Introduction	Understanding fundamentals of Statistics	Advanced statistics	Advanced statistics	Wrap up of understanding statistics with Python
Assisted practice	Measures of central tendency	Kurtosis skewness and T distribution	Bayes theorem	Basic statistics with Python
	Measures of dispersion	Hypothesis testing	Chi square distribution	Scipy for statistics
	Measures of shape	Type I and Type II errors	Goodness of Fit	Covering advanced statistics with python
	Covariance and correlation	null and alternate hypothesis	ANOVA	Break
		Confidence interval	F-distribution	Continued – Covering advanced statistics with python
		T-test , Z-test and P-value	F-test	Revisit important topics covered in previous classes
Assignment Discussion	Self study – Probability distribution	Exercise 3 – Solving exercise on topics practiced in class	Exercise 4 – Solving exercise on topics practiced in class	Self study – reference material. Implement the topics learnt in class

Week 3

In Person				Virtual
	Day 9	Day 10	Day 11	Sunday (Day 12)
	Assignment review			Assignment review
Introduction	Introduction to Machine Learning	Continued-Machine learning introduction	Regression	Logistic regression
Assisted practice	What is machine learning and types of machine learning	What is Outlier detection and its importance	Types of regression	Mathematical foundation
	Machine learning Pipeline	Z-score and IQR	Working with Linear regression	Types of Logistic regression (Binary, multinomial)
	Understanding Supervised learning	Understanding overfitting and underfitting	Assumptions of Linear regression (linearity relationship, autocorrelation, multicollinearity)	Assumptions of logistic regression
	Applications of supervised learning	Detect and prevent underfit and overfit	Model evaluation Metrics	Working with Cost function and Optimization
	Handling missing values	Handling missing values	Regularization techniques (L1, L2)	Break
	Encoding categorical variables			Handling imbalanced data
	Scaling numerical features			Model building
Assignment Discussion	Exercise 5 – Working on a dataset	Exercise 6 – Working on a dataset to implement the topics covered	Exercise 7 – Building Linear regression model	Exercise 8 – Data preparation and Building a Logistic regression model

Week 4

In Person				Virtual
	Day 13	Day 14	Day 15	Sunday (Day 16)
	Assignment review			Assignment review
Introduction	Classification	Optimization technique SGD	Decision Tree and Random Forest	Continued – Decision Tree and Random Forest
Assisted practice	Types of classification	Applying SGD	Understanding Decision Tree	Understanding how Random Forest works
	Selection of performance parameters	K Nearest Neighbors and its working	Giny impurity and Entropy	Hyperparameters of Random Forest ( max depth, min_samples_leaf etc)
	Introduction to Naïve Bayes	Choosing the right value for K	Decision tree for regression	Random forest for Classification ( majority voting and handling imbalanced classes )
	Working with Naïve Bayes classifier	Data preprocessing for KNN	Metric for evaluating the quality of split (MSE)	Break
	Training the Naïve Bayes model and prediction	Evaluating the performance metrics	Revisit splitting criteria in Decision Tree	Random forest for Regression (mean prediction and MSE)
	Applying smoothing technique	KNN use cases	Stopping criteria and pruning a Decision Tre	Hyperparameter tuning (Grid search, Random Search, Cross-validation)
	Performance evaluation	Understanding KNN disadvantages	Feature selection and handling missing values	Performance evaluation of model
Assignment Discussion	Exercise 8 – Building the model for spam detection	Exercise 9 – Building the model	Exercise 10 – Building the model	Exercise 11 – Building the model

Week 5

In Person				Virtual
	Day 17	Day 18	Day 19	Sunday (Day 20)
	Assignment review			Assignment review
Introduction	SVM	Continued – SVM	Revisit Week 4 and week 5	Case study and assessment
Assisted practice	Overview of SVM	Hyperparameter tuning -Grid search		Assessment on statistical concepts
	Hyperplane and margins	Hyperparameter tuning -Random Search
	Understanding maximum margin classifier	Model evaluation using cross validation method, confusion matrix		Break
	Linear Kernels	Understanding Class balance		Discussion and implementation of a case study
	Polynomial Kernel	Working with Oversampling		Linear Regression
	RBF	Discussion on real world examples		Logistic regression
	Experimenting with Kernels	Discussion on real world examples		Assessment on Supervised learning
	Load and visualize the dataset
	Evaluate with accuracy metrics
Assignment Discussion	Exercise 12 – Building the model on a given dataset	Exercise 13 – Building the model on a given dataset		Overview of topics to be covered in upcoming sessions

Week 6

In Person				Virtual
	Day 21	Day 22	Day 23	Sunday (Day 24)
	Assignment review
Introduction	Unsupervised learning	Hierarchical clustering	Principal Component Analysis	Continued – PCA
Assisted practice	Understanding types of unsupervised algorithms	Clustering – Hierarchical clustering	Purpose and applications	Understanding how to interpret visualization
	When to use unsupervised algorithm (anomaly detection)	Bottom up and top down approach	Working on a dataset to understand PCA	Discuss real world application of PCA
	Visualizing outputs	Applying Hierarchical clustering	Standardization of data	Explore datasets to work on unsupervised learning
	Understanding performance parameters	Understanding the dendrogram	Calculating the covariance matrix	Break
	Clustering – K-means	Practical use cases	Calculating eigen values and eigen vectors	Revisit the weeks activity
	Applying K-means clustering	Working with more examples	Selecting principal component	Compare the algorithms learnt and output obtained
	Visualizing clusters		Transforming the dataset
	Evaluating clustering performance		Visualization of transformed dataset
Assignment discussion	Exercise 15 – Building the model with given dataset	Exercise 16 – Building the model with given dataset	Exercise 17 – Building the model with topics covered in the day	Research on t-SNE (t-distributed Stochastic Neighbor Embedding) UMAP, LDA, Autoencoders

Week 7

In Person				Virtual
	Day 25	Day 26	Day 27	Sunday (Day 28)
	Assignment review			Assignment review
Introduction	Ensemble Learning	Ensemble Learning and Recommender system	Deep Learning	Deep Neural Network
Assisted practice	Types of ensemble methods -Bagging	Working with Stacking	Deep learning frameworks	Step by step implementation of forward propagation
	Boosting	Implementation of a recommender system using PyTorch	Lifecycle of a deep learning project	Step by step implementation of forward propagation
	Stacking		Neural network and types of neural network	Break
	Implementing bagging and random forest		Understanding perceptron	Implementing backward propagation
	Comparing the performance		Understanding forward propagation	Understanding and implementing loss function
	Understanding the limitations of Bagging	Collaborative filtering memory based model based	Understanding Activation functionz	Sequential APIs in TensorFlow
	Boosting to improve the model performance	Memory based – User based Item based	Backward propagation	Functional APIs in TensorFlow
	Understanding and implementing Boosting algorithms AdaBoost Gradient Boosting XGBoost		Gradient descent algorithm	Usage of Keras and Tensorflow Implementation of SGD Implementation of Momentum Implementation of Adagrad
Assignment discussion	Exercise 18 – Implement the Bagging and Boosting methods	Exercise 19 – Implement the Bagging, Boosting and stacking methods	Assignment – Document the theory behind Neural network covering the above topics	Exercise 20 – Using the framework learnt in the day implement all the functionality covered

Week 8

In Person				Virtual
	Day 29	Day 30	Day 31	Sunday (Day 32)
	Assignment review			Recurrent Neural Network (RNN)
Introduction	Batch Normalization	Convolutional Neural Network	Transfer Learning and Generative AI	Recurrent Neural Network (RNN)
Assisted practice	Implementation of Batch Normalization	CNN architecture	How to select pre-trained model	Overview of Transformers
	Exploding and vanishing gradient	Understanding ResNet	Advantages of transfer learning	Break
	Implementation of hyperparameter tuning	Filters and working of CNN	Usage of pre-trained model	Recap of all the topics covered
	Model interpretability	Understanding Pooling	Understanding generative AI	Discussion on real-world use cases
	Implementation of dropout	Implementation of image classification using CNN	Prompt engineering	Questions & Answers
	Implementation of early stopping	Advantages and Disadvantages of CNN. Usage of CNN	Practical use cases	Further reading and references
Assignment discussion	Exercise 21 – Implement neural network with the concepts covered in the day	Exercise 22 – Implement CNN model	Continue to work on the App to add more features leveraging GenAI APIs	What to do next.

Duration	In Person				Duration	Virtual
(minutes)		Day 1	Day 3	Day 3	(Minutes)	Sunday
10		Assignment review (Day 2 onwards)			20	Assignment review
20	Introduction	Essentials of Python Programming	Revisit day 1 topics and their implementation	Introduction to Statistical Analysis packages – Statsmodel and SciPy	15	Arithmetic operations and File handling
80	Assisted practice	Seeting up Jupyter Notebook	Working with CSV file	Scikit-learn	90	Conditional logic, Indexing and slicing
		Python functions	Working with Lambda function	Implement Statsmodel		File handling, Introduction to linear algebra
		Working with Python types	Understanding List comprehension	Implement Scipy		Scalars and vectors, dot product of vectors, norm of a vector
		Working with Python sequences	Python and data analysis	Common mathematical and statistical functions in NumPy		Matrix operations, transpose of a matrix, determinant of a matrix
		Python Strings	Understanding python packages available for data science	Evaluate webscaping techniques using BeatifulSoup		Eigenvalues and Eigenvectors
		Exploring Python Date and Time	Pandas, NumPy [Data manipulation]. Array shapes and axes in NumPy	Evaluate web scraping techniques using Scrapy	10	Break
		Python map() function and its usage	Matplotlib, seaborn, Plotly [Data visualization]		90	Statistics fundamentals, Data categorization and types
10	Assignment Discussion	Implement all the above functionality in a python program	Research on BeautifulSoup and scrapy. Exercise 1 – implementation of BeautifulSoap and Scrapy	Exercise 2 – Work on a sample dataset to create a dashboard using data visualization modules	15	Self study on basic statistical concepts to be covered in upcoming classes

Skills you'll gain

Generative AI

AI ethics

Natural Language Processing

Machine Learning

Artificial Intelligence

Workflow of Machine Learning projects

AI terminology

Workflow of Data Science projects

AI strategy

Pre-Requisites

Laptop

Basic understanding of programming (preferably Python)
Enthusiasm for learning AI & Machine Learning

Refund & Certification Policy

Refund Policy:

No Refunds: Cancellations made within 4 days (96 hours) of the training start date are non-refundable.
Full Refund: Cancellations made more than 4 days before the start date will receive a full refund after deducting bank or statutory charges.

Certification Requirement:

Minimum attendance of 80%.
Completion of all assigned tasks.

Artificial Intelligence /Machine Learning Course – Get Future Ready with AI Skills

Overview

Syllabus

Overview

Syllabus

Skills you'll gain

Pre-Requisites

Refund & Certification Policy

About Us

Useful Links

Contact Us

Support

Artificial Intelligence /Machine Learning Course – Get Future Ready with AI Skills

Overview

Syllabus

Overview

Syllabus

Skills you'll gain

Pre-Requisites

Refund & Certification Policy

About Us

Useful Links

Contact Us

Support

Welcome to HDSOFT Training

Your Path to Professional Growth!