shavi123/tensorflow2.0_notebooks

Implementation of a series of Neural Network architectures in TensorFow 2.0

Author: Ivan Bongiorni, Data Scientist at GfK; LinkedIn.

TensorFlow 2.0 Notebooks

This is a collection of my Notebooks on TensorFlow 2.0

The training of models is based on TensorFlow's eager execution method. I'll try to minimize referencese to Keras.

Summary of Contents:

• Basic feed forward stuff
• Autoencoders
• Convolutional Neural Networks
• Recurrent Neural Networks
• Applications to NLP

---

---

Contents:

Basic feed forward stuff:

1. Basic classifier: implementation of a feed forward Classifier with simple, full-Batch Gradient Descent in Eager execution.

2. Mini batch gradient descent: training a model with Mini Batch Gradient Descent.

3. Save and restore models: how to train a model, save it, then restore it and keep training.

4. Train a Neural Network with frozen layers

---

Autoencoders:

1. Autoencoder for dimensionality reduction: implementation of a stacked Autoencoder for dimensionality reduction of datasets.

2. Denoising Autoencoder (see CNN section below).

3. Recurrent Autoencoder (see RNN section below).

---

Convolutional Neural Networks:

1. Basic CNN classifier: a basic Convolutional Neural Network for multiclass classification.

2. Advanced CNN classifier with custom data augmentation.

3. Mixed-CNN classifier.

4. Denoising Autoencoder.

---

Recurrent Neural Networks:

1. LSTM many-to-one forecast model

2. LSTM many-to-many forecast model

3. Multivariate LSTM regression.

4. Seq2seq models.

---

RNN + Natural Language Processing

1. LSTM Text generator from this repository of mine.