Specialization - 12 course series
Introduction to AI & Machine Learning
Establishes foundational understanding of AI, ML, and Deep Learning. Covers key concepts, real-world applications, and industry overview.
Tools / Technologies: Python, Jupyter Notebook, Google Colab
Assignments : Write a comparative essay on AI vs ML vs DL; identify real-world use cases
-Logo_wine.png){kind=logo}
Python Programming for AI
Introduces Python fundamentals required for ML including data types, loops, functions, and libraries.
Tools / Technologies : Python, NumPy, Pandas
Assignments : Build basic Python programs; perform data manipulation
Data Preprocessing & Visualization
Covers data cleaning, transformation, handling missing values, and visualization techniques.
Tools / Technologies : Pandas, Matplotlib, Seaborn
Assignments : Clean a dataset and create visualizations (bar, scatter, heatmap)
Supervised Learning: Regression
Introduces regression models, linear regression, cost functions, and evaluation metrics.
Tools / Technologies : Scikit-learn
Assignments : Build a regression model (house price prediction); evaluate using metrics
Supervised Learning: Classification
Covers classification algorithms such as Logistic Regression, KNN, Decision Trees and evaluation techniques.
Tools : Scikit-learn
Outcome: Build a classification model; generate confusion matrix and accuracy report
Model Optimization & Feature Engineering
Focuses on improving models using feature engineering, cross-validation, and hyperparameter tuning.
Tools : Scikit-learn (GridSearchCV)
Outcome: Optimize previous models; create feature selection report
Unsupervised Learning
Introduces clustering (K-Means) and dimensionality reduction (PCA).
Tools : Scikit-learn
Outcome : Perform customer segmentation; visualize clusters
Introduction to Deep Learning
Covers neural networks, activation functions, and training basics.
Tools : TensorFlow, Keras
Outcome : Build and train a basic neural network model
Computer Vision
Introduces image processing and Convolutional Neural Networks (CNNs).
Tools : - TensorFlow/Keras, OpenCV
Outcome: Build an image classification model
Natural Language Processing (NLP)
Covers text preprocessing, tokenization, and sentiment analysis.
Tools : NLTK, spaCy
Outcome : Build a sentiment analysis model
.png)
Model Deployment & MLOps
Teaches model deployment, APIs, and introduction to MLOps practices.
Tools : Flask, Docker
Outcome : Deploy ML model as an API; build a simple interface
Capstone Project & Career Development
Final project integrating all concepts. Focus on portfolio, resume, and career pathways.
Tools : - GitHub, Kaggle
Outcome: Build and present end-to-end ML project; submit GitHub repo
Artificial intelligence & Machine Learning
Curriculum
LEVEL:
Beginner to Intermediate
FOCUS :
Core IT, Cloud Fundamentals, and Hands-on Cloud Deployment Skills
GOAL:
Prepare learners for foundational cloud roles and certifications (AWS CCP, AZ-900, GCP Digital Leader)
4.8 Reviews