Curriculum
Artificial Intelligence and Machine Learning
UNIT-I : Introduction to Machine Learning & Artificial Intelligence
Introduction Artificial Intelligence, History of Artificial Intelligence, ML Introduction, ML In Data Science, Applications of Machine Learning, DL Introduction, DL In Data Science, Use Cases of Artificial Intelligence, Scope of AI and ML, AI Tools & Packages
UNIT-II : Python, Python Libraries, Data Preprocessing
UNIT-II : Python, Python Libraries, Data Preprocessing
Python for Data Science, Basics of Python Conclusion – Self Assessment. Libraries required for Machine Learning –NumPy -Pandas -Matplotlib -Seaborn-Sklearn-Introduction tensorflow-Tensors-Creation-Operations-Transformation-Slicing - Introduction to Data preprocessing, Importing the Dataset, Handling Missing data - Mean, Median, Mode Working with categorical Data - OneHotEncoding, LabelEncoding, Finding Outliers, Handling Outliers using Quantile Method, Box Plot, Transformation Methods (Log, Reciprocal, Square root, Exponential, BoxCox), Feature Scaling, Splitting the data into Train and Test set, Feature Selection - Forward Selection, Backward Elimination
UNIT-III : Machine Learning with Tensorflow & Scikit-learn
UNIT-III : Machine Learning with Tensorflow & Scikit-learn
Models with tensors- creation-loading-classes-layers-Training with tensors-Gradient Optimizers-Losses-Performance-Metrics-Introduction to Supervised and Unsupervised Machine Learning-Regression Techniques – Simple Linear Regression – Multi Linear Regression – Polynomial Regression – Ridge and Lasso Regression – Classification Techniques – Logistic Regression–Decision tree–Random Forest–KNN –Naive Bayes –Support Vector Machines-Ensemble Techniques. Introduction to Tensorflow library-Random Forest Model, GradientBoosted Tree Model, Regression Evaluation Metrics, MAE, MSE, R Squared, RMSE, Classification metrics, Confusion Metrics, Accuracy, Precision, Recall, F1 Score, AUC ROC Curves
UNIT-IV : Introduction to Neural Network & Transfer Learning
UNIT-IV : Introduction to Neural Network & Transfer Learning
What is Deep Learning? - Deep Learning - Evolution and Business Potential - Introduction to Neural Networks-How do Neural Networks work -How do Neural Networks learn- Gradient Descent & its types- Backpropagation - Introduction to the Sequential Mode- Activation functions-Layers- Training-Loss function -Load-Preprocess Data - Images-Image Augmentation-Text- Building ANN Using TensorFlow - Evaluating Improving and Tuning ANN - Convolutional Neural Networks - Introduction to Convolutional Neural Networks - What are convolutional neural networks? - Building, Evaluating, Improving, and Tuning the CNN- Introduction to Transfer Learning Models - How does Transfer Learning Work? -When should we use Transfer Learning? -Approaches to transfer Learning -Inception V3 - Xception -
Resnet-50 - VGG16 & VGG-19.
UNIT-V : Web App Development
UNIT-V : Web App Development
Demonstrate fundamental understanding of machine Learning & artificial intelligence (AI) and its foundations.