Deep Learning Foundation Nanodegree

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 3h 55m | 5.55 GB

Become an expert in neural networks, and learn to implement them using the deep learning framework PyTorch. Build convolutional networks for image recognition, recurrent networks for sequence generation, generative adversarial networks for image generation, and learn how to deploy models accessible from a website.

Part 01 Neural Networks
Neural network is the bedrock to deep learning. In this section, you’ll learn how it works and test your ability by building a neural network from scratch.

Part 02 Convolutional Neural Networks
Convolutional neural network is the standard for solving vision problems. It’s used in self driving cars, face recognition, medical imaging, and a whole lot more! You’ll learn how this neural network works and apply to a image classification problem.

Part 03 Recurrent Neural Networks
Recurrent neural network is great for predicting on sequential data like music and text. With this neural network, you can generate new music, translate a language, or predict a seizure using an electroencephalogram. This section will teach you how to build and train a recurrent neural.

Part 04 Generative Adversarial Networks
Generative adversarial networks are a type of unsupervised learning where two neural networks compete against each other. This is commonly used to generate image data. You’ll learn how to build your own generative adversarial network and pit two neural networks against each other.

Part 05 Guaranteed Admission into your next Nanodegree
Utilize your guaranteed admission and enroll into a Career-Ready Nanodegree Program

Part 07 (Elective): Neural Networks
Neural networks are the bedrock to deep learning. In this section, you’ll learn how they work and test your ability by building a neural network from scratch.

Part 08 (Elective): Convolutional Neural Networks
Convolutional neural network is the standard for solving vision problems. It’s used in self driving cars, face recognition, medical imaging, and a whole lot more! You’ll learn how this neural network works and apply to a image classification problem.

Part 09 (Elective): Recurrent Neural Networks
Recurrent neural network is great for predicting on sequential data like music and text. With this neural network, you can generate new music, translate a language, or predict a seizure using an electroencephalogram. This section will teach you how to build and train a recurrent neural.

Part 10 (Elective): Generative Adversarial Networks
Generative adversarial networks are a type of unsupervised learning where two neural networks compete against each other. This is commonly used to generate image data. You’ll learn how to build your own generative adversarial network and pit two neural networks against each other.

Part 11 (Elective): Deep Reinforcement Learning
Use Reinforcement Learning algorithms like Q-Learning to train artificial agents to take optimal actions in an environment.