Master Deep Learning, and Break into AL
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.
Follow the suggested order or choose your own.
Designed to help you practice and apply the skills you learn.
Highlight your new skills on your resume or LinkedIn.
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.
Neural Networks and Deep LearningCurrent session: Dec 18
- 4 weeks of study, 3-6 hours a week
- 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 1Introduction to deep learningBe able to explain the major trends driving the rise of deep learning, and understand where and how it is applied today.Video · WelcomeVideo · What is a neural network?Video · Supervised Learning with Neural NetworksVideo · Why is Deep Learning taking off?Video · About this CourseReading · Frequently Asked QuestionsVideo · Course ResourcesReading · How to use Discussion ForumsQuiz · Introduction to deep learningVideo · Geoffrey Hinton interview
WEEK 2Neural Networks BasicsLearn to set up a machine learning problem with a neural network mindset. Learn to use vectorization to speed up your models.Video · Binary ClassificationVideo · Logistic RegressionVideo · Logistic Regression Cost FunctionVideo · Gradient DescentVideo · DerivativesVideo · More Derivative ExamplesVideo · Computation graphVideo · Derivatives with a Computation GraphVideo · Logistic Regression Gradient DescentVideo · Gradient Descent on m ExamplesVideo · VectorizationVideo · More Vectorization ExamplesVideo · Vectorizing Logistic RegressionVideo · Vectorizing Logistic Regression’s Gradient OutputVideo · Broadcasting in PythonVideo · A note on python/numpy vectorsVideo · Quick tour of Jupyter/iPython NotebooksVideo · Explanation of logistic regression cost function (optional)Quiz · Neural Network BasicsReading · Deep Learning Honor CodeReading · Programming Assignment FAQOther · Python Basics with numpy (optional)Practice Programming Assignment · Python Basics with numpy (optional)Other · Logistic Regression with a Neural Network mindsetProgramming Assignment · Logistic Regression with a Neural Network mindsetVideo · Pieter Abbeel interview
WEEK 3Shallow neural networksLearn to build a neural network with one hidden layer, using forward propagation and backpropagation.Video · Neural Networks OverviewVideo · Neural Network RepresentationVideo · Computing a Neural Network’s OutputVideo · Vectorizing across multiple examplesVideo · Explanation for Vectorized ImplementationVideo · Activation functionsVideo · Why do you need non-linear activation functions?Video · Derivatives of activation functionsVideo · Gradient descent for Neural NetworksVideo · Backpropagation intuition (optional)Video · Random InitializationQuiz · Shallow Neural NetworksOther · Planar data classification with a hidden layerProgramming Assignment · Planar data classification with a hidden layerVideo · Ian Goodfellow interview
WEEK 4Deep Neural NetworksUnderstand 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 networkVideo · Forward Propagation in a Deep NetworkVideo · Getting your matrix dimensions rightVideo · Why deep representations?Video · Building blocks of deep neural networksVideo · Forward and Backward PropagationVideo · Parameters vs HyperparametersVideo · What does this have to do with the brain?Quiz · Key concepts on Deep Neural NetworksOther · Building your Deep Neural Network: Step by StepProgramming Assignment · Building your deep neural network: Step by StepOther · Deep Neural Network – ApplicationProgramming Assignment · Deep Neural Network Application
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and OptimizationCurrent session: Dec 18
- 3 weeks, 3-6 hours per week
- 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 1Practical aspects of Deep LearningVideo · Train / Dev / Test setsVideo · Bias / VarianceVideo · Basic Recipe for Machine LearningVideo · RegularizationVideo · Why regularization reduces overfitting?Video · Dropout RegularizationVideo · Understanding DropoutVideo · Other regularization methodsVideo · Normalizing inputsVideo · Vanishing / Exploding gradientsVideo · Weight Initialization for Deep NetworksVideo · Numerical approximation of gradientsVideo · Gradient checkingVideo · Gradient Checking Implementation NotesQuiz · Practical aspects of deep learningOther · InitializationProgramming Assignment · InitializationOther · RegularizationProgramming Assignment · RegularizationOther · Gradient CheckingProgramming Assignment · Gradient CheckingVideo · Yoshua Bengio interview
WEEK 2Optimization algorithmsVideo · Mini-batch gradient descentVideo · Understanding mini-batch gradient descentVideo · Exponentially weighted averagesVideo · Understanding exponentially weighted averagesVideo · Bias correction in exponentially weighted averagesVideo · Gradient descent with momentumVideo · RMSpropVideo · Adam optimization algorithmVideo · Learning rate decayVideo · The problem of local optimaQuiz · Optimization algorithmsOther · OptimizationProgramming Assignment · OptimizationVideo · Yuanqing Lin interview
WEEK 3Hyperparameter tuning, Batch Normalization and Programming FrameworksVideo · Tuning processVideo · Using an appropriate scale to pick hyperparametersVideo · Hyperparameters tuning in practice: Pandas vs. CaviarVideo · Normalizing activations in a networkVideo · Fitting Batch Norm into a neural networkVideo · Why does Batch Norm work?Video · Batch Norm at test timeVideo · Softmax RegressionVideo · Training a softmax classifierVideo · Deep learning frameworksVideo · TensorFlowQuiz · Hyperparameter tuning, Batch Normalization, Programming FrameworksOther · TensorflowProgramming Assignment · Tensorflow
Structuring Machine Learning ProjectsCurrent session: Dec 18
- 2 weeks of study, 3-4 hours/week
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 1ML Strategy (1)Video · Why ML StrategyVideo · OrthogonalizationVideo · Single number evaluation metricVideo · Satisficing and Optimizing metricVideo · Train/dev/test distributionsVideo · Size of the dev and test setsVideo · When to change dev/test sets and metricsVideo · Why human-level performance?Video · Avoidable biasVideo · Understanding human-level performanceVideo · Surpassing human-level performanceVideo · Improving your model performanceReading · Machine Learning flight simulatorQuiz · Bird recognition in the city of Peacetopia (case study)Video · Andrej Karpathy interview
WEEK 2ML Strategy (2)Video · Carrying out error analysisVideo · Cleaning up incorrectly labeled dataVideo · Build your first system quickly, then iterateVideo · Training and testing on different distributionsVideo · Bias and Variance with mismatched data distributionsVideo · Addressing data mismatchVideo · Transfer learningVideo · Multi-task learningVideo · What is end-to-end deep learning?Video · Whether to use end-to-end deep learningQuiz · Autonomous driving (case study)Video · Ruslan Salakhutdinov interview
Convolutional Neural NetworksCurrent session: Dec 18
- 4 weeks of study, 4-5 hours/week
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 1Foundations of Convolutional Neural NetworksLearn 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 VisionVideo · Edge Detection ExampleVideo · More Edge DetectionVideo · PaddingVideo · Strided ConvolutionsVideo · Convolutions Over VolumeVideo · One Layer of a Convolutional NetworkVideo · Simple Convolutional Network ExampleVideo · Pooling LayersVideo · CNN ExampleVideo · Why Convolutions?Quiz · The basics of ConvNetsOther · Convolutional Model: step by stepProgramming Assignment · Convolutional Model: step by stepOther · Convolutional Model: applicationProgramming Assignment · Convolutional model: application
WEEK 2Deep convolutional models: case studiesLearn about the practical tricks and methods used in deep CNNs straight from the research papers.Video · Why look at case studies?Video · Classic NetworksVideo · ResNetsVideo · Why ResNets WorkVideo · Networks in Networks and 1×1 ConvolutionsVideo · Inception Network MotivationVideo · Inception NetworkVideo · Using Open-Source ImplementationVideo · Transfer LearningVideo · Data AugmentationVideo · State of Computer VisionQuiz · Deep convolutional modelsOther · Keras Tutorial – The Happy House (not graded)Other · Residual NetworksProgramming Assignment · Residual Networks
WEEK 3Object detectionLearn how to apply your knowledge of CNNs to one of the toughest but hottest field of computer vision: Object detection.Video · Object LocalizationVideo · Landmark DetectionVideo · Object DetectionVideo · Convolutional Implementation of Sliding WindowsVideo · Bounding Box PredictionsVideo · Intersection Over UnionVideo · Non-max SuppressionVideo · Anchor BoxesVideo · YOLO AlgorithmVideo · (Optional) Region ProposalsQuiz · Detection algorithmsOther · Car detection with YOLOv2Programming Assignment · Car detection with YOLOv2
WEEK 4Special applications: Face recognition & Neural style transferDiscover 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 LearningVideo · Siamese NetworkVideo · Triplet LossVideo · Face Verification and Binary ClassificationVideo · What is neural style transfer?Video · What are deep ConvNets learning?Video · Cost FunctionVideo · Content Cost FunctionVideo · Style Cost FunctionVideo · 1D and 3D GeneralizationsQuiz · Special applications: Face recognition & Neural style transferOther · Art generation with Neural Style TransferProgramming Assignment · Art generation with Neural Style TransferOther · Face Recognition for the Happy HouseProgramming Assignment · Face Recognition for the Happy House
Sequence ModelsStarts December 2017
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.
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.