Master Deep Learning, and Break into AL

 

Master Deep Learning, and Break into A

 

About This Specialization

If you want to break into AI, this Specialization will help you do so. Deep Learning is one of the most highly sought after skills in tech. We will help you become good at Deep Learning.

In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach.

You will also hear from many top leaders in Deep Learning, who will share with you their personal stories and give you career advice.

AI is transforming multiple industries. After finishing this specialization, you will likely find creative ways to apply it to your work.

We will help you master Deep Learning, understand how to apply it, and build a career in AI.

Created by:

Industry Partners:

 

courses 5 courses

Follow the suggested order or choose your own.

projects Projects

Designed to help you practice and apply the skills you learn.

    certificates Certificates

Highlight your new skills on your resume or LinkedIn.

Projects Overview

You will see and work on case studies in healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will also build near state-of-the-art deep learning models for several of these applications. In a “Machine Learning flight simulator”, you will work through case studies and gain “industry-like experience” setting direction for an ML team.

deeplearning.ai is also partnering with the NVIDIA Deep Learning Institute (DLI) to provide labs in advanced, application-specific topics and to give learners access to GPUs for programming assignments. This will give you an opportunity to build deep learning projects in a cutting-edge, industry-like environment.

Courses
  1. COURSE 1

    Neural Networks and Deep Learning

    Current session: Dec 18
    Commitment
    4 weeks of study, 3-6 hours a week
    Subtitles
    English, Chinese (Traditional)

    About the Course

    If you want to break into cutting-edge AI, this course will help you do so. Deep learning engineers are highly sought after, and mastering deep learning will give you numerous new career opportunities. Deep learning is also a new “superpower” that will let you build AI systems that just weren’t possible a few years ago. In this course, you will learn the foundations of deep learning. When you finish this class, you will: – Understand the major technology trends driving Deep Learning – Be able to build, train and apply fully connected deep neural networks – Know how to implement efficient (vectorized) neural networks – Understand the key parameters in a neural network’s architecture This course also teaches you how Deep Learning actually works, rather than presenting only a cursory or surface-level description. So after completing it, you will be able to apply deep learning to a your own applications. If you are looking for a job in AI, after this course you will also be able to answer basic interview questions. This is the first course of the Deep Learning Specialization.


    WEEK 1
    Introduction to deep learning
    Be able to explain the major trends driving the rise of deep learning, and understand where and how it is applied today.

     

    Video · Welcome

     

    Video · What is a neural network?

     

    Video · Supervised Learning with Neural Networks

     

    Video · Why is Deep Learning taking off?

     

    Video · About this Course

     

    Reading · Frequently Asked Questions

     

    Video · Course Resources

     

    Reading · How to use Discussion Forums

     

    Quiz · Introduction to deep learning

     

    Video · Geoffrey Hinton interview

    WEEK 2
    Neural Networks Basics
    Learn to set up a machine learning problem with a neural network mindset. Learn to use vectorization to speed up your models.

     

    Video · Binary Classification

     

    Video · Logistic Regression

     

    Video · Logistic Regression Cost Function

     

    Video · Gradient Descent

     

    Video · Derivatives

     

    Video · More Derivative Examples

     

    Video · Computation graph

     

    Video · Derivatives with a Computation Graph

     

    Video · Logistic Regression Gradient Descent

     

    Video · Gradient Descent on m Examples

     

    Video · Vectorization

     

    Video · More Vectorization Examples

     

    Video · Vectorizing Logistic Regression

     

    Video · Vectorizing Logistic Regression’s Gradient Output

     

    Video · Broadcasting in Python

     

    Video · A note on python/numpy vectors

     

    Video · Quick tour of Jupyter/iPython Notebooks

     

    Video · Explanation of logistic regression cost function (optional)

     

    Quiz · Neural Network Basics

     

    Reading · Deep Learning Honor Code

     

    Reading · Programming Assignment FAQ

     

    Other · Python Basics with numpy (optional)

     

    Practice Programming Assignment · Python Basics with numpy (optional)

     

    Other · Logistic Regression with a Neural Network mindset

     

    Programming Assignment · Logistic Regression with a Neural Network mindset

     

    Video · Pieter Abbeel interview

    WEEK 3
    Shallow neural networks
    Learn to build a neural network with one hidden layer, using forward propagation and backpropagation.

     

    Video · Neural Networks Overview

     

    Video · Neural Network Representation

     

    Video · Computing a Neural Network’s Output

     

    Video · Vectorizing across multiple examples

     

    Video · Explanation for Vectorized Implementation

     

    Video · Activation functions

     

    Video · Why do you need non-linear activation functions?

     

    Video · Derivatives of activation functions

     

    Video · Gradient descent for Neural Networks

     

    Video · Backpropagation intuition (optional)

     

    Video · Random Initialization

     

    Quiz · Shallow Neural Networks

     

    Other · Planar data classification with a hidden layer

     

    Programming Assignment · Planar data classification with a hidden layer

     

    Video · Ian Goodfellow interview

    WEEK 4
    Deep Neural Networks
    Understand the key computations underlying deep learning, use them to build and train deep neural networks, and apply it to computer vision.

     

    Video · Deep L-layer neural network

     

    Video · Forward Propagation in a Deep Network

     

    Video · Getting your matrix dimensions right

     

    Video · Why deep representations?

     

    Video · Building blocks of deep neural networks

     

    Video · Forward and Backward Propagation

     

    Video · Parameters vs Hyperparameters

     

    Video · What does this have to do with the brain?

     

    Quiz · Key concepts on Deep Neural Networks

     

    Other · Building your Deep Neural Network: Step by Step

     

    Programming Assignment · Building your deep neural network: Step by Step

     

    Other · Deep Neural Network – Application

     

    Programming Assignment · Deep Neural Network Application

  2. COURSE 2

    Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

    Current session: Dec 18
    Commitment
    3 weeks, 3-6 hours per week
    Subtitles
    English, Chinese (Traditional), Chinese (Simplified)

    About the Course

    This course will teach you the “magic” of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow. After 3 weeks, you will: – Understand industry best-practices for building deep learning applications. – Be able to effectively use the common neural network “tricks”, including initialization, L2 and dropout regularization, Batch normalization, gradient checking, – Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. – Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance – Be able to implement a neural network in TensorFlow. This is the second course of the Deep Learning Specialization.


    WEEK 1
    Practical aspects of Deep Learning

     

    Video · Train / Dev / Test sets

     

    Video · Bias / Variance

     

    Video · Basic Recipe for Machine Learning

     

    Video · Regularization

     

    Video · Why regularization reduces overfitting?

     

    Video · Dropout Regularization

     

    Video · Understanding Dropout

     

    Video · Other regularization methods

     

    Video · Normalizing inputs

     

    Video · Vanishing / Exploding gradients

     

    Video · Weight Initialization for Deep Networks

     

    Video · Numerical approximation of gradients

     

    Video · Gradient checking

     

    Video · Gradient Checking Implementation Notes

     

    Quiz · Practical aspects of deep learning

     

    Other · Initialization

     

    Programming Assignment · Initialization

     

    Other · Regularization

     

    Programming Assignment · Regularization

     

    Other · Gradient Checking

     

    Programming Assignment · Gradient Checking

     

    Video · Yoshua Bengio interview

    WEEK 2
    Optimization algorithms

     

    Video · Mini-batch gradient descent

     

    Video · Understanding mini-batch gradient descent

     

    Video · Exponentially weighted averages

     

    Video · Understanding exponentially weighted averages

     

    Video · Bias correction in exponentially weighted averages

     

    Video · Gradient descent with momentum

     

    Video · RMSprop

     

    Video · Adam optimization algorithm

     

    Video · Learning rate decay

     

    Video · The problem of local optima

     

    Quiz · Optimization algorithms

     

    Other · Optimization

     

    Programming Assignment · Optimization

     

    Video · Yuanqing Lin interview

    WEEK 3
    Hyperparameter tuning, Batch Normalization and Programming Frameworks

     

    Video · Tuning process

     

    Video · Using an appropriate scale to pick hyperparameters

     

    Video · Hyperparameters tuning in practice: Pandas vs. Caviar

     

    Video · Normalizing activations in a network

     

    Video · Fitting Batch Norm into a neural network

     

    Video · Why does Batch Norm work?

     

    Video · Batch Norm at test time

     

    Video · Softmax Regression

     

    Video · Training a softmax classifier

     

    Video · Deep learning frameworks

     

    Video · TensorFlow

     

    Quiz · Hyperparameter tuning, Batch Normalization, Programming Frameworks

     

    Other · Tensorflow

     

    Programming Assignment · Tensorflow

  3. COURSE 3

    Structuring Machine Learning Projects

    Current session: Dec 18
    Commitment
    2 weeks of study, 3-4 hours/week
    Subtitles
    English

    About the Course

    You will learn how to build a successful machine learning project. If you aspire to be a technical leader in AI, and know how to set direction for your team’s work, this course will show you how. Much of this content has never been taught elsewhere, and is drawn from my experience building and shipping many deep learning products. This course also has two “flight simulators” that let you practice decision-making as a machine learning project leader. This provides “industry experience” that you might otherwise get only after years of ML work experience. After 2 weeks, you will: – Understand how to diagnose errors in a machine learning system, and – Be able to prioritize the most promising directions for reducing error – Understand complex ML settings, such as mismatched training/test sets, and comparing to and/or surpassing human-level performance – Know how to apply end-to-end learning, transfer learning, and multi-task learning I’ve seen teams waste months or years through not understanding the principles taught in this course. I hope this two week course will save you months of time. This is a standalone course, and you can take this so long as you have basic machine learning knowledge. This is the third course in the Deep Learning Specialization.


    WEEK 1
    ML Strategy (1)

     

    Video · Why ML Strategy

     

    Video · Orthogonalization

     

    Video · Single number evaluation metric

     

    Video · Satisficing and Optimizing metric

     

    Video · Train/dev/test distributions

     

    Video · Size of the dev and test sets

     

    Video · When to change dev/test sets and metrics

     

    Video · Why human-level performance?

     

    Video · Avoidable bias

     

    Video · Understanding human-level performance

     

    Video · Surpassing human-level performance

     

    Video · Improving your model performance

     

    Reading · Machine Learning flight simulator

     

    Quiz · Bird recognition in the city of Peacetopia (case study)

     

    Video · Andrej Karpathy interview

    WEEK 2
    ML Strategy (2)

     

    Video · Carrying out error analysis

     

    Video · Cleaning up incorrectly labeled data

     

    Video · Build your first system quickly, then iterate

     

    Video · Training and testing on different distributions

     

    Video · Bias and Variance with mismatched data distributions

     

    Video · Addressing data mismatch

     

    Video · Transfer learning

     

    Video · Multi-task learning

     

    Video · What is end-to-end deep learning?

     

    Video · Whether to use end-to-end deep learning

     

    Quiz · Autonomous driving (case study)

     

    Video · Ruslan Salakhutdinov interview

  4. COURSE 4

    Convolutional Neural Networks

    Current session: Dec 18
    Commitment
    4 weeks of study, 4-5 hours/week
    Subtitles
    English

    About the Course

    This course will teach you how to build convolutional neural networks and apply it to image data. Thanks to deep learning, computer vision is working far better than just two years ago, and this is enabling numerous exciting applications ranging from safe autonomous driving, to accurate face recognition, to automatic reading of radiology images. You will: – Understand how to build a convolutional neural network, including recent variations such as residual networks. – Know how to apply convolutional networks to visual detection and recognition tasks. – Know to use neural style transfer to generate art. – Be able to apply these algorithms to a variety of image, video, and other 2D or 3D data. This is the fourth course of the Deep Learning Specialization.


    WEEK 1
    Foundations of Convolutional Neural Networks
    Learn to implement the foundational layers of CNNs (pooling, convolutions) and to stack them properly in a deep network to solve multi-class image classification problems.

     

    Video · Computer Vision

     

    Video · Edge Detection Example

     

    Video · More Edge Detection

     

    Video · Padding

     

    Video · Strided Convolutions

     

    Video · Convolutions Over Volume

     

    Video · One Layer of a Convolutional Network

     

    Video · Simple Convolutional Network Example

     

    Video · Pooling Layers

     

    Video · CNN Example

     

    Video · Why Convolutions?

     

    Quiz · The basics of ConvNets

     

    Other · Convolutional Model: step by step

     

    Programming Assignment · Convolutional Model: step by step

     

    Other · Convolutional Model: application

     

    Programming Assignment · Convolutional model: application

    WEEK 2
    Deep convolutional models: case studies
    Learn about the practical tricks and methods used in deep CNNs straight from the research papers.

     

    Video · Why look at case studies?

     

    Video · Classic Networks

     

    Video · ResNets

     

    Video · Why ResNets Work

     

    Video · Networks in Networks and 1×1 Convolutions

     

    Video · Inception Network Motivation

     

    Video · Inception Network

     

    Video · Using Open-Source Implementation

     

    Video · Transfer Learning

     

    Video · Data Augmentation

     

    Video · State of Computer Vision

     

    Quiz · Deep convolutional models

     

    Other · Keras Tutorial – The Happy House (not graded)

     

    Other · Residual Networks

     

    Programming Assignment · Residual Networks

    WEEK 3
    Object detection
    Learn how to apply your knowledge of CNNs to one of the toughest but hottest field of computer vision: Object detection.

     

    Video · Object Localization

     

    Video · Landmark Detection

     

    Video · Object Detection

     

    Video · Convolutional Implementation of Sliding Windows

     

    Video · Bounding Box Predictions

     

    Video · Intersection Over Union

     

    Video · Non-max Suppression

     

    Video · Anchor Boxes

     

    Video · YOLO Algorithm

     

    Video · (Optional) Region Proposals

     

    Quiz · Detection algorithms

     

    Other · Car detection with YOLOv2

     

    Programming Assignment · Car detection with YOLOv2

    WEEK 4
    Special applications: Face recognition & Neural style transfer
    Discover how CNNs can be applied to multiple fields, including art generation and face recognition. Implement your own algorithm to generate art and recognize faces!

     

    Video · What is face recognition?

     

    Video · One Shot Learning

     

    Video · Siamese Network

     

    Video · Triplet Loss

     

    Video · Face Verification and Binary Classification

     

    Video · What is neural style transfer?

     

    Video · What are deep ConvNets learning?

     

    Video · Cost Function

     

    Video · Content Cost Function

     

    Video · Style Cost Function

     

    Video · 1D and 3D Generalizations

     

    Quiz · Special applications: Face recognition & Neural style transfer

     

    Other · Art generation with Neural Style Transfer

     

    Programming Assignment · Art generation with Neural Style Transfer

     

    Other · Face Recognition for the Happy House

     

    Programming Assignment · Face Recognition for the Happy House

  5. COURSE 5

    Sequence Models

    Starts December 2017
    Subtitles
    English

    About the Course

    This course will teach you how to build models for natural language, audio, and other sequence data. Thanks to deep learning, sequence algorithms are working far better than just two years ago, and this is enabling numerous exciting applications in speech recognition, music synthesis, chatbots, machine translation, natural language understanding, and many others. You will: – Understand how to build and train Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs. – Be able to apply sequence models to natural language problems, including text synthesis. – Be able to apply sequence models to audio applications, including speech recognition and music synthesis. This is the fifth and final course of the Deep Learning Specialization.

Creators

deeplearning.ai is dedicated to advancing AI by sharing knowledge about the field. We hope to welcome more individuals into deep learning and AI.

deeplearning.ai is Andrew Ng’s new venture which amongst others, strives for providing comprehensive AI education beyond borders.

 

Enroll Now

 

FREE Wordpress blog setup service

FREE Wordpress blog setup service

Ad: Yes, I will not charge you a single dime for setting up your blog based on WordPress. Click here for more information

Mobile App Creation

Mobile App Creation Service

Ad: Get a mobile app based on your website. Get it published under Google Play and Apple app store in no time! Get more visitors towards your business. Click here for more information