A project about the brief implementation of MLP, CNN, RNN, Unsupervised learning with Autoencoders, ETC, Text analytics using CNN in Python
- Regression tasks with MLP
- Classification tasks with MLP
- Weight initialization schemes
- Activation functions (Nonlinearity)
- Batch normalization
- Optimizers
- Dropout
- Ensemble of models
- Putting it altogether
- Basics of CNN architecture
- Getting deeper with CNNs
- CNN for sentence classification (imdb)
- Importing models already trained on ImageNet dataset (keras.applications)
- Understanding RNN architecture
- Vanilla RNN (SimpleRNN)
- Stacked vanilla RNN
- LSTM
- Stacked LSTM
- Deep RNNs
- Bidirectional RNNs
- Deep bidirectional RNNs
- CNN-RNN
- CuDNN LSTM
- CuDNN GRU
- Autoencoder basics
- Convolutional autoencoder
- Dimensionality reduction using autoencoder
- Sequential API
- Model Functional API
- Importing images
- ModelCheckpoint
- EarlyStopping
- ReduceLROnPlateau
- Make your training process faster with CUDA & CuDNN
- Cross validation
- Grid search
- Random search
- Learning under class imbalance situations
- Getting model weights
- Loading & saving model weights
- Simple RNN model
- Stacked RNN model
- Bidirectional RNN model
- Simple LSTM model
- Stacked LSTM model
- Bidirectional LSTM model
- Simple GRU model
- Stacked GRU model
- Bidirectional GRU model
- Simple MLP
- Autoencoder + MLP (dimensionality reduction)
- Generating similar questions with seq2seq model
- CNN-static implementation of Kim 2014 paper
- Sentiment analysis with Logistic Regression (using sklearn & TF)
- Sentiment analysis with RNN
Section with emphasis on text data analytics
- 1-D Convolution for text analysis
- CNN for setnence classification (Kim 2014)
- Dynamic CNN for sentence modeling (Kalchbrenner et al 2014)
- CNN for text categorization (Johnson and Zhang 2014)