The Deep Learning Specialization is a foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology.

In this Specialization, you will build and train neural network architectures such as Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, Transformers, and learn how to make them better with strategies such as Dropout, BatchNorm, Xavier/He initialization, and more. Get ready to master theoretical concepts and their industry applications using Python and TensorFlow and tackle real-world cases such as speech recognition, music synthesis, chatbots, machine translation, natural language processing, and more.

AI is transforming many industries. The Deep Learning Specialization provides a pathway for you to take the definitive step in the world of AI by helping you gain the knowledge and skills to level up your career. Along the way, you will also get career advice from deep learning experts from industry and academia.

Learn more at: https://www.coursera.org/specializations/deep-learning

In the first course of the Deep Learning Specialization, you will study the foundational concept of neural networks and deep learning. Learn more at: https://www.coursera.org/learn/neural-networks-deep-learning

There's no correlations between files, so you're free to check them however you like, however, I recommend you to see it in this order, so you can see my progress.

1. vectorization: A simple file showing why it's best not to use loops, but vectorize stuff.
2. math_basics: A series of simple mathematical functions just to remember myself of basic calculus and linear algebra.
3. cat-classifier-v1: My first ever Cat classifier, I used a linear regression model with a neural network mindset. The code reads a 64x64 image and decides if it's a cat image or not. You can put your own images in it and try, check the end of the notebook.
4. data-class-1-hidden: A neural network with 1 hidden layer to classify a dataset with a 'flower-like' shape.
5. utils.py: A series of functions to be used with 'cat-classifier-v2.ipynb'
6. cat-classifier-v2: Second version of the cat classifier, this time using deep neural networks. Improved accuracy.

In the second course of the Deep Learning Specialization, you will open the deep learning black box to understand the processes that drive performance and generate good results systematically. Learn more at: https://www.coursera.org/learn/deep-neural-network

There's no correlations between files, so you're free to check them however you like, however, I recommend you to see it in this order, so you can see my progress.

1. initialization: How to initialize W and B to best fit the model.
2. regularization: Checking and resolving overfitting problems.
3. gradient-checking: Checking the gradient descent of a N-Model.
4. optimization: Optimizing hyperparameters for better accuracy and cost.
5. tensorflow: A first try using TensorFlow.

In the third course of the Deep Learning Specialization, you will learn how to build a successful machine learning project and get to practice decision-making as a machine learning project leader. Learn more at: https://www.coursera.org/learn/machine-learning-projects

This course doesn't have any practical exercises.

In the fourth course of the Deep Learning Specialization, you will understand how computer vision has evolved and become familiar with its exciting applications such as autonomous driving, face recognition, reading radiology images, and more. Learn more at: https://www.coursera.org/learn/convolutional-neural-networks

There's no correlations between files, so you're free to check them however you like, however, I recommend you to see it in this order, so you can see my progress.

1. CNN_Step_by_step: Creating a Convolutional Neural Network from scratch.
2. CNN_Application: Creating a Convolutional Neural Network with TensorFlow and Keras, using it with real cases (smile and numbers on sign language detector).
3. Residual_Networks: Building a CONV2D neural network.
4. MobileNetV2: Using Mobile Net V2 to train an alpaca detector.
5. Car_Detection: Using YOLO to create a car (amongst other objects) detection model
6. Art_Generation: Using VGG-19 to generate art from images.

In the fifth and last course of the Deep Learning Specialization, you will become familiar with sequence models and their exciting applications such as speech recognition, music synthesis, chatbots, machine translation, natural language processing (NLP), and more. Learn more at: https://www.coursera.org/learn/nlp-sequence-models

There's no correlations between files, so you're free to check them however you like, however, I recommend you to see it in this order, so you can see my progress.

1. Dinossaur_Names: Generating Dinossaur names using Recurrent Neural Networks.
2. Jazz_Solo: Training a neural network to learn jazz and create a song afterwards.