Classical ML, model evaluation, deep learning, computer vision and NLP with TensorFlow, Keras and PyTorch. Build, evaluate, tune and explain machine learning and deep learning models, and ship an end-to-end capstone.
Learners comfortable with Python and Pandas who want to build and evaluate ML models.
Classes, objects, inheritance, encapsulation, polymorphism, exception handling, and reusable ML utility classes
AI versus ML, types of machine learning, supervised, unsupervised, and reinforcement learning; ML workflow: data, features, training, validation, testing, and deployment considerations
Linear regression, logistic regression, decision boundaries, feature scaling, train-test splitting, overfitting, underfitting, and regularization
Classification metrics: accuracy, precision, recall, F1-score, confusion matrix, ROC-AUC; regression metrics: MAE, MSE, RMSE, R²; cross-validation, hyperparameter tuning, and bias-variance trade-off
K-Means clustering, choosing the number of clusters, elbow method, silhouette score, PCA, dimensionality reduction, and interpretation of clusters
End-to-end supervised and unsupervised ML pipeline: data cleaning, feature engineering, modeling, evaluation, visualization, and business interpretation
Neural networks, perceptrons, activation functions, loss functions, optimizers, forward and backward propagation, model compilation, training, and evaluation
Convolution, filters, feature maps, pooling, flattening, dense layers, image preprocessing, augmentation, transfer learning concepts, and model evaluation
Text preprocessing, tokenization, stemming, lemmatization, Bag-of-Words, TF-IDF, word embeddings, RNNs, LSTM, GRU, and long-term dependencies
Integrated AI/ML solution combining Python OOP, data preparation, classical ML or deep learning, evaluation, visualization, documentation, and responsible-use considerations
Fill in your details to see the complete syllabus with hands-on labs and hours, or ask us to call you back.
Predict customers likely to churn and recommend retention actions
Classify claims as low, medium, or high risk using policy and customer data
Segment customers and recommend targeted marketing strategies
Predict disease risk from clinical or lifestyle data with strong evaluation controls
Classify news articles as real or fake using text features
Classify posts or reviews as positive, negative, or neutral
Classify common road signs from images and display the predicted class
Detect and label products in shelf images
40 hours of live, instructor-led training, of which about 32 hours are hands-on labs, projects and a capstone.
Learners comfortable with Python and Pandas who want to build and evaluate ML models.
Build, evaluate, tune and explain machine learning and deep learning models, and ship an end-to-end capstone.
scikit-learn, TensorFlow, Keras, PyTorch and Pandas.
Tell us your background and we will confirm whether this is the right level and share batch dates.
+91 98809 82425WhatsApp us