rxhith / deep-learning-lab

Deep-Learning-Lab

According to Syllabus

1. Familiarize basic python packages for deep learning such as Keras, Tensorflow etc.

2. Data pre-processing operations such as outliers and/or inconsis- tent data value management. **

3. Implement Feed forward neural network with three hidden layers for classification on CIFAR-10 dataset.**

4. Analyse the impact of optimization and weight initialization tech- niques such as Xavier initialization, Kaiming Initialization, dropout and regularization techniques and visualize the change in perform- ance. **

5. Digit classification using CNN architecture for MNIST dataset. **

6. Digit classification using pre-trained networks like VGGnet-19 for MNIST dataset and analyse and visualize performance improve- ment.**

7. Implement a simple RNN for review classification using IMDB data- set.**

8. Analyse and visualize the performance change while using LSTM and GRU instead of simple RNN.**

According to my Record

1. Outlier detection
2. Linear Classification
3. Image classification on MNIST (Any pre-built dataset)
4. Image classification on CIFAR-10
5. Weight Initialization Optimizer analysis
6. Optimizer analysis
7. VGGnet-19
8. RNN for IMDb
9. LSTM and GRU for IMDb
10. ANN based image classifier