Fundamentals of Deep Learning Lab (AIML355)

Lab record templates aligned with the university experiment list. Replace placeholders with your dataset source, code, outputs, plots, observations, and viva answers. (Minimum: 8 experiments to be performed.)

Course Objectives
  1. Implement deep learning models in Python and train them with real-world datasets.
  2. Implement CNN, RNN and Deep Learning NLP models in Python.
Course Outcomes
  • CO1: Design and implement CNN for object classification from images/video.
  • CO2: Implement Autoencoder, RNN, LSTM (variants) and Deep NLP.
Start Experiment Back to Theory
Find an experiment
Type to filter the list.
Tip: Keep the same write-up order in every experiment (Aim → Dataset → Procedure → Code → Output → Discussion → Viva).
Exp 1 — TensorFlow & Keras basics Template
Open the record-ready template and fill with your work.
Exp 2 — ANN for regression & classification Template
Open the record-ready template and fill with your work.
Exp 3 — CNN for MRI dataset Template
Open the record-ready template and fill with your work.
Exp 4 — Autoencoder for dimensionality reduction Template
Open the record-ready template and fill with your work.
Exp 5 — Autoencoder on image dataset Template
Open the record-ready template and fill with your work.
Exp 6 — Conv layers performance (MNIST) Template
Open the record-ready template and fill with your work.
Exp 7 — RNN for stock price prediction Template
Open the record-ready template and fill with your work.
Exp 8 — LSTM weather prediction Template
Open the record-ready template and fill with your work.
Exp 9 — Transfer learning (MobileNetV2) Template
Open the record-ready template and fill with your work.
Exp 10 — Transfer learning (VGG16) Template
Open the record-ready template and fill with your work.
Exp 11 — NLP analysis of restaurant reviews Template
Open the record-ready template and fill with your work.
Exp 12 — Spam detection with TF-IDF Template
Open the record-ready template and fill with your work.
Tip: press Esc to close.