Deep Learning

Deep Learning

1. Introduction to Multi-layer perceptron, Neural Network, Introduce hardware for deep learning
2. Convolutional Neural Networks (History, Convolution and pooling)
3. Loss Functions and Optimization
4. Activation functions and initialization of Weight Matrices
5. Regularization ( dropout, batch normalization)
6. Introduction to Tensorflow and Keras (Frameworks for deep learning)
7. Format the dataset to feed into the Neural Network
8. Implement simple 2D Convolution Neural Network
9. Introduction to data augmentation and transfer learning
10. Improve previous network by transfer learning using data augmentation
11. CNN Architectures (AlexNet, VGG, GoogLeNet, ResNe)
12. RNN (LSTM, GRU)
13. Advance Topics based on Interest (Faster R-CNN, Mask R-CNN, GAN)
Posted on: May 9, 2020admin