Become an Artificial Intelligence Developer

Master Artificial Intelligence & Machine Learning: A Comprehensive Educational Course

Learn directly from the AI developers working in the industry

Weekday Batch: 8 PM - 9 PM | Weekend Batch: 2 PM - 4 PM

Start Now

Why Choose AI / ML?

High Demand for Skills: AI and ML expertise are highly sought-after in various industries, offering numerous job opportunities.
Career Advancement: Enhances your resume, opening doors to higher-level positions and better salaries.
Diverse Applications: Skills are applicable across multiple industries, from healthcare and finance to retail and manufacturing.
Problem-Solving Abilities: Develop analytical and methodical approaches to tackle complex challenges.
Innovation and Impact: Equips you to contribute to technological advancements and innovations in various fields.
Certification: Earn a recognized credential that validates your expertise and enhances your professional credibility.

Course Content

Python Programming

1. Programming

1.1 Core Python

Expressions
Variables
Data Structures (Lists, Tuples, Dictionaries, Sets)
Functions
Packages
Project Structuring

1.2 File Handling

Read Files
Write/Create Files
Delete Files

1.2.1 Exception Handling:

Try, Except blocks for error handling

1.3 Python libraries

NumPy

Arrays and Vectorized Operations
Mathematical Functions

Pandas

DataFrame and Series

1.4 Python Matplotlib and Seaborn

Mathplotlib

Basic Plotting
Customising Plots (Titles, Labels, Legends)
Plot Styles and Themes

Seaborn

Statistical data visualtion library based on matplotlib

Data Preparation and Exploration

2.1 Data Collection and Cleaning

Data Formats (CSV, JSON, XML)
Web Scraping (BeautifulSoup, Selenium)
Handling Missing Data
Data Cleaning Techniques

2.2 Exploratory Data Analysis (EDA)

Descriptive Statistics
Data Visualization Techniques
Feature Engineering, LIME

2.3 Data Transformation and Preprocessing

Scaling and Normalisation
Encoding Categorical Variables
Handling Imbalanced Data
Handling Outlier

Introduction to Machine Learning

3.1 Overview of Machine Learning

Definition and Types of Machine Learning ( Supervised, Unsupervised, Reinforcement Learning)
Applications and Impact of Machine Learning in Various Industries

3.2 Mathematical Foundations for Machine Learning

Linear Algebra Concepts for ML ( Vectors, Matrices, Operations)
Probability and statistics for ML (Probability Distributions, Bayes Theorem, Hypothesis Testing)
Calculus Essentials ( Derivatives, Gradient Descent)

Supervised Learning

4.1 Regression Algorithms

Linear Regression,Polynomial Regression
Regularization Techniques (Ridge, Lasso) to overcome challenges of overfitting and underfitting

4.2 Classification Algorithms

Logistic Regression , Decesion Trees,Random FOrests
Support Vector Machines (SVM), k-nearest Neighbours (k-NN)

4.3 Model Evaluation and Selection

Cross-Validation Techniques (k-Fold, Stratified K-Fold)
Performance Metrics: Accuracy, Precision, Recall, F1 Score, ROC-AUC Curve

4.4 Hyperparameter Tuning and Fine-Tuning

Grid Search
Random Seatch
Bayesian Optimization
Hyperopt
Automated Hyperparamater Tuning using frameworks like sci-kit-optimise or Optuna

Decision Trees / Random Forests: Tuning max depth, min samples split, etc.
Support Vector Machines, Tuning kernel type, C parameter

4.5 Mini Project: Date Fruits Classification

Description:-The project aims to apply machine learning algorithms to classify date fruits (Barhee, Deglet Nour, Sukkary, Rotab Mozafati, Ruthana, Safawi, Sagai) based on physical characteristics such as area, perimeter, eccentricity, and colour statistics. The goal is to achieve accurate classification and evaluate model performance using metrics like accuracy and F1-score.

Techniques specific to algorithms:

Unsupervised Learning

5.1 Clustering Algorithms

Hierarchical Clustering
Density-Based Clustering (DBSCAN)
Gaussian Mixture Models (GMM)

5.2 Dimensionality Reduction

Principal Component Analysis(PCA)
t-Distributed Stochastic Neighbour Embedding (t-SNE)
Linear Discriminant Analusis (LDA)

5.3 Anomaly Detection

Statistical Methods
Machine Learning Methods:

Isolation Forest
One-Class SVM
Autoencoders for Anomaly Detection

5.4 Hyperparameter Tuning and Fine-Tuning

Techniques specific to algorithms:

K-Means:Tuning numbers of clusters, initialisation method

DBSCAN:Tuning epsilon, minimum samples
Gaussian Mixture Models:Tuning number of components,covariance type

5.5 Mini Project:- Customer Personality Analysis

Description:- This clustering project involves analysing customer data including demographics (Year_Birth, Education, Marital_Status, Income), household information (Kidhome, Teenhome), customer tenure (Dt_Customer), transaction history (Recency, MntWines), and various marketing campaign responses (AcceptedCmp1 through AcceptedCmp5). The goal is to segment customers into meaningful clusters based on these attributes, enabling targeted marketing strategies and personalised customer engagement initiatives.

Advanced Topics in Machine Learning

6.1 Ensemble Methods

Boosting:

AdaBoost
Gradient Boosting Machines (GBM)
xgboost
CatBoost
LightGbm

Stacking and Blending Models

6.2 Hyperparameter Tuning and Fine-Tuning

Techniques specific to algorithms:

Decision Trees / Random Forests:

Tuning max depth,min samples split, etc.

Support Vector Machines:

Tuning kernel type, C parameter
Other Algorithms as applicable

6.3 Mini project:- Indians Diabetes Prediction

Description:- This project aims to predict the onset of diabetes in female patients of Pima Indian heritage using medical predictor variables such as number of pregnancies, BMI, insulin levels, and age. The dataset includes demographic and diagnostic measurements, with the target variable 'Outcome' indicating whether a patient has diabetes or not. The objective is to develop a predictive model that accurately classifies patients based on these variables, facilitating early intervention and personalised healthcare strategies.

Natural Language Processing and LLM

7.1 Text Preprocessing

Handling Rare Words and Out-of-vocabulary Tokens

Libraries and Tools:

NLTK:Natural Language Toolkit for text processing tasks
spaCy:Advanced NLP library for tokeniztion, named entity recognition , and more
textBlob:simplified text processing using NLP tasks like sentiment analysis and Pos tagging

7.2 Word Embeddings

Word2Vec, GloVe, FastText
Contextual Embeddings (e.g, ELMo, BERT)

Libraries and Tools:

Hugging Face Transformers:

State-of-pre-rained embeddings like BERT, GPT, etc.
WordCloud: Visual Representation of word frequency using word clouds

7.3 NLP Tasks

Sentiment analysis
Named Entity Recognition (NER)
Text Classification
Machine Translation
LDA (Latent Dirichet Allocation)

Libraries and Tools:

spaCy:

NER and text classification capabilities

Hugging Face Transformers:

For advanced NLP tasks like sentiment analysis,NER, and text classification using pre-trained models

7.4 Sequence-to-Sequence Models and Transformers

Attention Mechanism
Transformer Architecture
Applications in NLP (e.g., BERT, GPT)

Libraries and Tools:

Hugging Face Transformers:

State-of-the-art transformer models for sequence-to-sequence tasks, summariztion, and more

7.5 LLM (Large Language model)

OPENAI
LANGchain
Google Gemini
Generative AI

7.6 Mini Project:-RAG Based Chatbot

Description:- A Retrieval-Augmented Generation (RAG) based chatbot combines retrieval-based and generation-based methods to provide accurate and contextually relevant responses. Retrieval-based models search a large corpus for relevant information, while generation-based models create coherent responses, ensuring accuracy and natural language generation.

Deep Learning

8.1 Basics of Neural Networks

Perceptrons and Multi-layer Perceptrons (MLPs)
Activation Functions (e.g, RELU, Sigmoid, Tanh)
Loss Functions (e.g, Cross-Entropy, Mean Squared Error)
Optimisation Algorithms (e.g, Gradient Descent, Adam)

8.2 Convolutional Neural Networks (CNNs)

Architecture and Components (Convolutional Layers, Pooling Layers)
Popular CNN architectures (e.g LeNet, AlexNet, ResNet)
Applications in Image Recognition and Computer Vision

8.3 Recurrent Neural Networks
(RNNs)

Architecture and Components (recurrent Layers, LSTM, GRU)
Applications in Sequence Modeling (e.g,Natural Language Processing, Time Series Analysis)

8.4 Transfer Learning and Fine-
Tuning

Pre-trained Models(e.g, VGG,ResNEt)
Fine-tuning Techiques:

Freezing Layers
Learning Rate Scheduling
Gradient Clipping

8.5 Tools and Important Libraries

Hugging Face Transformers:
State-of-the-art transformer models and libraries
TensorFlow: Open-source deep learning framework by Google.
PyTorch: Deep learning framework known for its flexibility and ease of use.
MLFlow: Open-source platform for managing the end-to-end machine learning lifecycle
Encoder-Decoder Models:
Architecture used for sequence-to-sequence tasks like machine translation.
Hugging Face Transformers:
Library for state-of-the-art NLP using transformer models

8.6 Minor Project:-Image Captioning Using Flickr 8k dataset

Description:-The aim of this project is to develop a deep learning-based system that automatically generates descriptive captions for images. This involves training a model to interpret image content and produce coherent, contextually relevant text descriptions. The project combines computer vision
and natural language processing techniques.

Model Deployment (MLOps)

9.1 System Design

9.2 Building and Deploying Machine Learning Models

Containerization (e.g. Docker, Kubernetes)
Deployment (e.g., AWS Sagemaker, AWS Serverless)
CI/CD Pipelines

9.3 Integration with Web Frameworks

9.4 Asynchronous Processing and
Event-Driven Architectures

Celery: Distributed task queue for handling asynchronous tasks
Integration with Python applications for background job processing
Kafka: Distributed event streaming platform Pre-trained Models(e.g. VGG, ResNEt)
Fine-tuning Techiques:
Real-time data processing and
messaging for scalable applications
Redis and RabbitMQ

FastAPI: Building fast web APIs with Python and async support
Flask: Lightweight web framework for Python
RESTful APIs: Designing APIs for machine learning models

Serialisation and Deserialization of Data
Handling HTTP Requests and Responses
Authentication and Authorization

9.5 Major Project:-
1. Mobile price Prediction Microservices Using FastAPI/Flask

Description:-This project involves building a web application that predicts the price range of mobile phones based on features such as battery capacity, camera quality, RAM, internal storage, etc. Using FastAPI, Flask, or Django frameworks, the application will provide a user-friendly interface for users to input mobile specifications and receive predicted price ranges. Machine learning models trained on a dataset of mobile phone features and prices will power the prediction engine, enabling users to make informed decisions while buying or selling mobile devices.

2.TextProcessingHub Microservices
using 20_newsGroup Datasets

Description:-Text Processing Hub aims to be a scalable platform for advanced text analysis, enabling users to perform topic modelling, named entity recognition, and sentiment analysis on large volumes of unstructured text data. By integrating modern technologies like FastAPI for web APIs, Kafka, Celery for task management, and Docker for containerization, the project showcases a robust infrastructure for efficient and effective text processing.

Model Monitoring and Maintenance

10.1 Continuous Monitoring of Model Performance

Logging and Metrics Collection
Alerting Systems for Anomalies
Model Drift Detection and Management

Register now to take a leap in your career

Course fee

Mohali: INR 30,000 (EMI Plan: 3 x INR 12,000)

Online: INR 20,000 (EMI Plan: 3 x INR 8,000)

Group Discount - 5% for a group of 5, 10% for a group of 10

Note:

1.Enter your email in the notes/comments while making UPI payment.

2.Fill the form in the website footer, providing same email and

submit payment screenshot as attachment.

Why Avi Skill?

The same standards of training followed as for the employees of Avisoft.
Training from the developers working in the industry, and not instructors at training institutes.
Pre-placement job opportunities from Avisoft and partner companies at STPI Mohali.

"My experience with Avi Skill has profoundly shaped my professional career. We created several projects using AI & ML, which helped me solidify my understanding and identify gaps in my knowledge. The support and guidance I received from seniors, management and colleagues have given my career a significant head start."

Waseem Riyaz

tech@aviskill.com

+91 8899001123

Master Artificial Intelligence & Machine Learning: A Comprehensive Educational Course

Learn directly from the AI developers working in the industry

Weekday Batch: 8 PM - 9 PM | Weekend Batch: 2 PM - 4 PM

Why Choose AI / ML?

Course Content

Python Programming

1. Programming

1.1 Core Python

Expressions

Variables

Data Structures (Lists, Tuples, Dictionaries, Sets)

Functions

Packages

​Project Structuring

1.2 File Handling

Read Files

Write/Create Files

Delete Files

1.2.1 Exception Handling:

Try, Except blocks for error handling

1.3 Python libraries

NumPy

Arrays and Vectorized Operations

Mathematical Functions

Pandas

DataFrame and Series

1.4 Python Matplotlib and Seaborn

Mathplotlib

Basic Plotting

Customising Plots (Titles, Labels, Legends)

Plot Styles and Themes​

Seaborn

Statistical data visualtion library based on matplotlib

Data Preparation and Exploration

2.1 Data Collection and Cleaning

Data Formats (CSV, JSON, XML)

Web Scraping (BeautifulSoup, Selenium)

Handling Missing Data

Data Cleaning Techniques

2.2 Exploratory Data Analysis (EDA)

Descriptive Statistics

Data Visualization Techniques

Feature Engineering, LIME

2.3 Data Transformation and Preprocessing

Scaling and Normalisation

Encoding Categorical Variables

Handling Imbalanced Data

Handling Outlier

Introduction to Machine Learning

​3.1 Overview of Machine Learning

Definition and Types of Machine Learning ( Supervised, Unsupervised, Reinforcement Learning)

Applications and Impact of Machine Learning in Various Industries

​3.2 Mathematical Foundations for Machine Learning

Linear Algebra Concepts for ML ( Vectors, Matrices, Operations)

Probability and statistics for ML (Probability Distributions, Bayes Theorem, Hypothesis Testing)

Calculus Essentials ( Derivatives, Gradient Descent)​

Supervised Learning

​4.1 Regression Algorithms

Linear Regression,Polynomial Regression

Regularization Techniques (Ridge, Lasso) to overcome challenges of overfitting and underfitting

​4.2 Classification Algorithms

Logistic Regression , Decesion Trees,Random FOrests

Support Vector Machines (SVM), k-nearest Neighbours (k-NN)

​4.3 Model Evaluation and Selection

Cross-Validation Techniques (k-Fold, Stratified K-Fold)

Performance Metrics: Accuracy, Precision, Recall, F1 Score, ROC-AUC Curve

4.4 Hyperparameter Tuning and Fine-Tuning

Grid Search

Random Seatch

Bayesian Optimization

Hyperopt

Automated Hyperparamater Tuning using frameworks like sci-kit-optimise or Optuna

Decision Trees / Random Forests: Tuning max depth, min samples split, etc.

Support Vector Machines, Tuning kernel type, C parameter

4.5 Mini Project: Date Fruits Classification

​

Techniques specific to algorithms:

Unsupervised Learning

Project Structuring

Plot Styles and Themes

3.1 Overview of Machine Learning

3.2 Mathematical Foundations for Machine Learning

Calculus Essentials ( Derivatives, Gradient Descent)

4.1 Regression Algorithms

4.2 Classification Algorithms

4.3 Model Evaluation and Selection

5.1 Clustering Algorithms

5.5 Mini Project:- Customer Personality Analysis

Advanced Topics in Machine Learning

6.1 Ensemble Methods

6.2 Hyperparameter Tuning and Fine-Tuning

Techniques specific to algorithms:

Decision Trees / Random Forests:

Support Vector Machines:

6.3 Mini project:- Indians Diabetes Prediction

7.4 Sequence-to-Sequence Models and Transformers