List of Experiments / Activities
- DEEP LEARNING LAB
- 1Write a python program to Implement Perceptron for understanding single-layer neural network?
- 2Write a program to Visualize Activation Functions (Sigmoid, ReLU, Tanh)?
- 3Write a program to Build a Simple Feedforward Neural Network?
- 4Write a program to MNIST Digit Classification using Keras?
- 5Write a program to Create and Visualize CNN Layers.
- 6Write a program to CIFAR-10 Image Classification for understanding Multiclass image classification using CNN.
- 7Write a program to implement Image Augmentation Techniques for application of preprocessing & transformation?
- 8Write a program using Dropout for Regularisation to improve model generalisation.
- 9Write a program to Build Model Using PyTorch?
- 10Write a program to Compare Training with and without Batch Normalization for Analyzing performance and convergence?
- Note: The Instructor may add/delete/modify/tune experiments
Course Outcomes (COs)
After completion of the course student will be able to:
- CO1Understand the fundamentals of neural networks and activation functionsK2
- CO2Implement and visualize basic feedforward and convolutional neural networksK4
- CO3Train, validate, and evaluate deep learning models on standard datasetsK5
- CO4Use popular deep learning libraries such as TensorFlow/Keras or PyTorchK3
- CO5Apply deep learning concepts to real-world use cases like image classification and digit recognitionK5
Note: The AKTU syllabus PDF of some branches prints this subject with small differences in the experiments (AI & Data Science, CSE (AI), CSE (AI & ML), CSE (Data Science)). Please also check the official AKTU PDF of your branch, linked at the end of your semester page.
Official AKTU syllabus
This subject is on page 8 of the original AKTU PDF.