Deep Learning Journey

Description: My collected learning notebooks for Deep Learning and AI in general.

My current interest: Tensorflow, Computer Vision, Machine Learning.

---

What I have learned for Tensorflow Certificate Exam (You can use this as a checklist for preparation):

Resources: Daniel Bourke

(1) Tensorflow Basics

• Build and train neural network models using TensorFlow 2.x

• Build, compile and train machine learning (ML) models using TensorFlow.

• Preprocess data to get it ready for use in a model.

• Use models to predict results.

• Build sequential models with multiple layers.

• Build and train models for binary classification.

• Build and train models for multi-class categorization.

• Plot loss and accuracy of a trained model.

• Identify strategies to prevent overfitting, including augmentation and dropout.

• Use pretrained models (transfer learning).

• Extract features from pre-trained models.

• Ensure that inputs to a model are in the correct shape.

• Ensure that you can match test data to the input shape of a neural network.

• Ensure you can match output data of a neural network to specified input shape for test data.

• Understand batch loading of data.

• Use callbacks to trigger the end of training cycles.

• Use datasets from different sources.

• Use datasets in different formats, including json and csv.

• Use datasets from tf.data.datasets.

(2) Image classification

• Define Convolutional neural networks with Conv2D and pooling layers.

• Build and train models to process real-world image datasets.

• Understand how to use convolutions to improve your neural network.

• Use real-world images in different shapes and sizes.

• Use image augmentation to prevent overfitting.

• Use ImageDataGenerator.

• Understand how ImageDataGenerator labels images based on the directory structure.

(3) Natural language processing (NLP)

• Build natural language processing systems using TensorFlow.

• Prepare text to use in TensorFlow models.

• Build models that identify the category of a piece of text using binary categorization

• Build models that identify the category of a piece of text using multi-class categorization

• Use word embeddings in your TensorFlow model.

• Use LSTMs in your model to classify text for either binary or multi-class categorization.

• Add RNN layers to your model.

• Use RNNS, LSTMs and CNNs in models that work with text.

• Train LSTMs on existing text to generate text (such as songs and poetry)

(4) Time series, sequences and predictions

• Train, tune and use time series, sequence and prediction models.

• Prepare data for time series learning.

• Understand Mean Average Error (MAE) and how it can be used to evaluate accuracy of sequence models.

• Use RNNs and CNNs for time series, sequence and forecasting models.

• Identify when to use trailing versus centred windows.

• TensorFlow Certificate Candidate Handbook 3

• Use TensorFlow for forecasting.

• Prepare features and labels.

• Identify and compensate for sequence bias.

• Adjust the learning rate dynamically in time series, sequence and prediction models.

Study references:

• ProtonX AI and VietAI School

• Daniel Bourke's Youtube Channel and his video on Tensorflow preparation: Link: https://www.youtube.com/watch?v=ya5NwvKafDk&ab_channel=DanielBourke

• Laurence Moroney's Tensorflow course on Coursera

• "Foundational Deep Learning" book by Tuan Nguyen, "Foundational Machine Learning" book by Ph.D. Tiep Vu

---

My next plans:

• Do more in-depth studies in Deep Learning, starting with GANs and Photogrammetry