This 400 hours course has been designed for people with basic knowledge in machine learning and decent programming skills. We recommend to be familiar with linear algebra (matrix multiplication) and calculus (multivariable derivatives).
You will gain excellent theoretical knowledge of deep-learning concepts, and bring high-level theory to life using cutting-edge frameworks such as TensorFlow, Keras and PyTorch.
You will study convolutional networks, recurrent networks, generative adversarial networks and deep reinforcement learning. You’ll have the opportunity to prove your skills by building several projects and will gain exclusive insights from working professionals in the field.
01 – Neural Networks Basics: maths crash course, machine learning review, perceptron implementation.
02 – Deep Learning Fundamentals: multi-layer perceptron, backpropagation, activation functions, dropout, gradient descent, neural networks training.
03 – Big Data Engineering: Hadoop, MapReduce, Spark & PySpark, Elastic Search, Docker, Teradata, Jenkin, Paperspace, AWS and Google Cloud.
04 – Convolutional Neural Networks (CNN): image classification, weight initialization, auto encoder, transfer learning.
05 – Recurrent Neural Networks (RNN): text generation, RNN and LSTM implementation, hyperparameters, embeddings, sentiment prediction.
06 – Generative Adversarial Networks (GAN): deep convolutional GAN, semi-supervised GAN.
07 – Reinforcement Learning (RL): Monte-Carlo methods, Q-Learning, Deep Q-Network, policy gradients, Gym.