B.E. (Computer Engineering) Deep Learning Lab Syllabus - Mumbai University 2026
The University has moved this degree onto NEP 2020 one year at a time. The first and second years are NEP 2020 syllabi; the third and fourth years are still examined on the REV-2019 'C' Scheme, which is what the University sets for them this year.
Loading syllabus...
Syllabus for Deep Learning Lab
Lab Objectives
- 1 To implement basic neural network models for simulating logic gates.
- 2 To implement various training algorithms for feedforward neural networks.
- 3 To design deep learning models for supervised, unsupervised and sequence learning. Lab Outcomes: At the end of the course, the students will be able to
- 1 Implement basic neural network models to learn logic functions.
- 2 Design and train feedforward neural networks using various learning algorithms.
- 3 Build and train deep learning models such as Autoencoders, CNNs, RNN, LSTM etc.
Suggested List of Experiments
- 1 Based on Module 1 (Any two) using Virtual Lab
- 1 Implement Mc-Culloch Pitts model for binary logic functions.
- 2 Implement Perceptron algorithm to simulate any logic gate.
- 3 Implement Multilayer Perceptron algorithm to simulate XOR gate.
- 4 To explore python libraries for deep learning e.g. Theano, TensorFlow etc.
- 2 Module 2 (Any Two)
- 5 Apply any of the following learning algorithms to learn the parameters of the supervised single layer feed forward neural network. a. Stochastic Gradient Descent b. Mini Batch Gradient Descent c. Momentum GD d. Nestorev GD e. Adagrad GD f. Adam Learning GD
- 6 Implement a backpropagation algorithm to train a DNN with at least 2 hidden layers.
- 7 Design and implement a fully connected deep neural network with at least 2 hidden layers for a classification application. Use appropriate Learning Algorithm, output function and loss function.
- 4 Module 3 (Any One)
- 8 Design the architecture and implement the autoencoder model for Image Compression.
- 9 Design the architecture and implement the autoencoder model for Image denoising.
- 5 Module 4 (Any One)
- 10 Design and implement a CNN model for digit recognition application.
- 11 Design and implement a CNN model for image classification.
- 6 Module 5 (Any One)
- 12 Design and implement LSTM for Sentiment Analysis.
- 13 Design and implement GRU for classification on text data.
- 14 Design and implement RNN for classification of temporal data. Term Work:
- 1 Term work should consist of 8 experiments.
- 2 The final certification and acceptance of term work ensures satisfactory performance of laboratory work and minimum passing marks in term work.
- 3 The final certification and acceptance of term work ensures satisfactory performance of laboratory work and minimum passing marks in term work. Total 25 Marks (Experiments: 15-marks, Attendance Theory & Practical: 05-marks, Assignment: 05-marks) Practical and Oral exam Based on the entire syllabus of CSDC8011: Deep Learning and CSDL8011: Deep Learning Lab
Reproduced from the University of Mumbai syllabus for B.E. (Computer Engineering) under REV-2019 'C' Scheme, in force from the academic year 2022-23. Wording is as printed in that syllabus. The University sets no module list for this course; what she publishes is the objectives, outcomes and assessment guidelines reproduced above.
The complete syllabus
This subject is cut from the University circular for its year. Open a document here if you want the whole thing rather than a single subject.