Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

The course is contained knowledge that are useful to work on deep learning as an engineer. Simple neural networks & training, CNN, Autoencoders and feature extraction, Transfer learning, RNN, LSTM, NLP, Data augmentation, GANs, Hyperparameter tuning, Model deployment and serving are included in the course.

License

NotificationsYou must be signed in to change notification settings

MrinmoiHossain/Udacity-Deep-Learning-Nanodegree

Repository files navigation

Udacity Deep Learning Nanodegree

N.B.: Please don't use the assignment and quiz solution. Try to solve the problem by yourself.


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. -Source

Books

Resources

AI, ML, DL

Backpropagation

Optimizers

Style Transfer

CNN

LSTMs

Reinforcement learning

Residual Learning

Attention

GAN

Batch Normalization

Machine Learning Workflow

Cloud ML

GitHub

Hackathons

Neural Network Frameworks

Keras

Others

Extra Projects

Core Curriculum

1. Introduction to Deep Learning

Get your first taste of deep learning by applying style transfer to your own images, and gain experience using development tools such as Anaconda and Jupyter notebooks.

Lesson-1: Welcome to the Deep Learning Nanodegree Program

NoLessonTopicLink/Source
1Welcome to the Deep Learning Nanodegree ProgramApplication of Deep LearningSource/GitHub
2Meet Your InstructorsInstructors-Matt, Luis and CezanneSource/GitHub
3Program StructureCourse outline, Chapter Introduction, Project GuidelinesGitHub
4Community GuidelinesDetails about the community rulesGitHub
5PrerequisitesRequired programming and math skillsGitHub
6Getting Set UpRequired tools-Anaconda, Jupyter NotebookSource

Lesson-2: Nanodegree Career Sevices

NoLessonTopicLink/Source
1Access the Career PortalCareer portal guidelinesGitHub
2Prepare for the Udacity Talent ProgramRequirements for udacity profile, complete udacity profileGitHub

Lesson-3: Welcome to Udacity

NoLessonTopicLink/Source
1What It TakesDescription of Udacity NanodegreeSource/GitHub
2Project ReviewsProject review and feedback systemSource/GitHub
3KnowledgeTell about knowledge sharing websiteSource
4Mentors and Student HubHelping support of the course - mentors and student hubSource
5Community InitiativesCommunity introduction, project milestone and everyday challengeSource
6Meet the Careers TeamCareer guide lines for the mentorsSource/GitHub
7Introduction to the Career PortalCreate my career profileSource/GitHub
8Access Your Career PortalHow to improve my career portalSource/GitHub
9Your Udacity Professional ProfileUdacity Professional Profile features important, professional informationSource/GitHub
10Prepare for the Udacity Talent ProgramUdacity Talent Program, update udacity profileSource/GitHub

Lesson-4: Get Help with Your Account

NoLessonTopicLink/Source
1Frequently Asked Questions (FAQ)Frequently asked question and forumSource
2SupportDiscuss about help centerSource

Lesson-5: Anaconda

NoLessonTopicLink/Source
1InstructorInstructor-Mat Leonard, welcome about anacondaSource/GitHub
2IntroductionConda or Anaconda installation stepSource
3What is Anaconda?Anaconda's description, managing packages and environmentsSource/GitHub
4Installing AnacondaInstalling AnacondaSource
5Managing packagesManaging packages systemSource/GitHub
6Managing environmentsManaging and the using of the environmentsSource/GitHub
7More environment actionsSaving, loading, listing and removing environmentsSource/GitHub
8Best practicesUsing and sharing environmentsSource/GitHub
9On Python versions at UdacityWhy Python version-3 is used this courseSource/GitHub

Lesson-6: Applying Deep Learning

NoLessonTopicLink/Source
1IntroductionOverview of the lessonSource/GitHub
2Style TransferOverview about the style transferSource/GitHub
3DeepTrafficIntroduction the deepTrafic (application DL)Source/GitHub
4Flappy BirdDL application in Flappy BirdSource/GitHub
5Books to ReadSome suggested books for DLSource/GitHub

Lesson-7: Jupyter Notebooks

NoLessonTopicLink/Source
1InstructorOverview of Jupyter Notebook and Introduce the Mat Leonard, instructorSource/GitHub
2What are Jupyter notebooks?Introduction of jupyter notebook, Literate programming and How notebooks workGitHub
3Installing Jupyter NotebookInstalling process of Jupyter NotebookSource/GitHub
4Launching the notebook serverLaunching and shutdowing the notebook serverSource/GitHub
5Notebook interfaceNotebook interface - tool bar, command palette etcSource/GitHub
6Code cellsWhat is Code cells and uses of itSource/GitHub
7Markdown cellsWritting procedure of markdown cells - headers, emphasis, code, math expressionsSource/GitHub
8Keyboard shortcutsKeyboard shortcutsSource/GitHub
9Magic keywordsTiming code, Embedding visualizations, DebuggingSource/GitHub
10Converting notebooksConverting notebooks in differents file formatSource/GitHub
11Creating a slideshowCreating and Running a slideshowSource/GitHub
12Finishing upSummary and finish messageSource/GitHub

Lesson-8: Matrix Math and NumPy Refresher

NoLessonTopicLink/Source
1IntroductionMatrix and importance in Deep LearningSource/GitHub
2Data DimensionsData dimensions - scalers, vector, matrix, tensorsSource/GitHub
3Data in NumPyNumPy IntroductionSource/GitHub
4Element-wise Matrix OperationsMatrices element wise operationSource/GitHub
5Element-wise Operations in NumPyMatrices element wise operation using NumPySource/GitHub
6Matrix Multiplication: Part 1Dot multiplication, element wise multiplication in metricesSource/GitHub
7Matrix Multiplication: Part 2Important note about matrix multiplicationSource/GitHub
8NumPy Matrix MultiplicationNumPy Matrix MultiplicationSource/GitHub
9Matrix TransposesMatrix Transposes and where use of itSource/GitHub
10Transposes in NumPyTransposes matrices in NumPySource/GitHub
11NumPy QuizShort programming quiz that asks to use a few NumPy featuresGitHub

2. Neural Networks

Learn neural networks basics, and build your first network with Python and NumPy. Use the modern deep learning framework PyTorch to build multi-layer neural networks, and analyze real data.

Lesson-1: Introduction to Neural Networks

Lesson-2: Implementing Gradient Descent

Lesson-3: Training Neural Networks

Lesson-4: GPU Workspaces Demo

Lesson-5: Sentiment Analysis

Lesson-6: Deep Learning with PyTorch

3. Convolutional Neural Networks

Learn how to build convolutional networks and use them to classify images (faces, melanomas, etc.) based on patterns and objects that appear in them. Use these networks to learn data compression and image denoising.

Lesson-1: Convolutional Neural Networks

Lesson-2: Cloud Computing

Lesson-3: Transfer Learning

Lesson-4: Weight Initialization

Lesson-5: Autoencoders

Lesson-6: Style Transfer

Lesson-7: Deep Learning for Cancer Detection

Lesson-8: Jobs in Deep Learning

4. Recurrent Neural Networks

Build your own recurrent networks and long short-term memory networks with PyTorch; perform sentiment analysis and use recurrent networks to generate new text from TV scripts.

Lesson-1: Recurrent Neural Networks

Lesson-2: Long Short-Term Memory Networks (LSTMs)

Lesson-3: Implementation of RNN & LSTM

Lesson-4: Hyperparameters

Lesson-5: Embedding & Word2Vec

Lesson-6: Sentiment Prediction RNN

NoLessonTopicLink/Source
1Sentiment RNN, IntroductionLSTM example, Sentiment analysisSource/GitHub
2Pre-Notebook: Sentiment RNNImplementing a complete RNN that can classify the sentiment of movie reviewsSource
3Notebook: Sentiment RNNImplementing a complete RNN that can classify the sentiment of movie reviewsGitHub
4Data Pre-ProcessingImport data, Remove punctuation, Split data into listGitHub
5Encoding Words, SolutionEncoding the word & label as conver to word to integersGitHub
6Getting Rid of Zero-LengthSet all the input size as standard, remove zero len data and modify high len dataGitHub
7Cleaning & Padding DataRemoving zero length dataGitHub
8Padded Features, SolutionPad or truncate all data to a specific lengthGitHub
9TensorDataset & Batching DataSplit the train-validation-test data, Data loaded from numpy to tensor, Data loaded with batch sizeGitHub
10Defining the ModelIntroduction about the model of the networkGitHub
11Complete Sentiment RNNInitialize the model parameters, Feedforward network, Backpropagation, Initializes hidden stateGitHub
12Training the ModelHyperparameters, Loss function and OptimizationGitHub
13TestingTesting the modelGitHub
14Inference, SolutionInferenceGitHub

Lesson-7: Attention

NoLessonTopicLink/Source
1Introduction to AttentionIntroduction and defination of Attention, Application and where uses attentionSource/GitHub
2Encoders and DecodersSequence-to-sequence models, encoders, decodersSource/GitHub
3Sequence to Sequence RecapReview of sequence-to-sequence models, encoders, decodersSource/GitHub
4Encoding -- Attention OverviewOverview of encoding in AttentionSource/GitHub
5Decoding -- Attention OverviewOverview of decoding in AttentionSource/GitHub
6Attention OverviewExample and question about attentionSource/GitHub
7Attention EncoderBehind the scenario of encoder algorithms in attentionSource/GitHub
8Attention DecoderBackbone of decoder and the Attention decoder phaseSource/GitHub
9Attention Encoder & DecoderQuiz about encoder and decoderSource/GitHub
10Bahdanau and Luong AttentionBahdanu/Additive Attention and Luong/Multiplicative Attention Model IntroductionSource/GitHub
11Multiplicative AttentionDetails architecture of Multiplicative AttentionSource/GitHub
12Additive Attention3-Concat attention and details architecture of Additive AttentionSource/GitHub
13Additive and Multiplicative AttentionQuiz: Additive and Multiplicative AttentionSource/GitHub
14Computer Vision ApplicationsExample of computer vision applications with attentionSource/GitHub
15Other Attention MethodsThe transformer models and indside of the model (encoder and decoder part)Source/GitHub
16The Transformer and Self-AttentionFull details of the Transformer and Self-Attention architectureSource/GitHub
17Notebook: Attention BasicsAttention Basic function-Scoring, Annotations Matrix, Softmax, Attention Context VectorGitHub
18[SOLUTION]: Attention BasicsAttention Basic function-Scoring, Annotations Matrix, Softmax, Attention Context VectorGitHub
19OutroEnding message and remainder the most important information in that dataSource/GitHub

5. Generative Adversarial Networks

Learn to understand and implement a Deep Convolutional GAN (generative adversarial network) to generate realistic images, with Ian Goodfellow, the inventor of GANs, and Jun-Yan Zhu, the creator of CycleGANs.

Lesson-1: Generative Adversarial Networks

NoLessonTopicLink/Source
1Introducing Ian GoodFellowIntroduction about Ian Goodfellow and his experienceSource/GitHub
2Applications of GANsWhat you can do with GAN, as- text to images, art to realistic image, face to cartoon, dat to night mode, unsupervised image-to-image, Imitation learningSource/GitHub
3How GANs workAutoregressive model, Process of GAN, Generator models & DiscriminatorSource/GitHub
4Games and EquilibriaGame theory, Rock-Paper-Scissors game, Equilibriam situtationSource/GitHub
5Tips for Training GANsGAN layers architecture, activation and loss functions for generator & discriminator, batch normalizationSource/GitHub
6Generating Fake ImagesExcercise dataset introduction, MNIST dataset - fake or real imageSource/GitHub
7MNIST GANBuilt a GAN to generate new images of handwritten digitsSource/GitHub
8GAN Notebook & DataIntroduction the excercise and datasetsSource/GitHub
9Pre-Notebook: MNIST GANAll about generating new images of handwritten digitsSolution
10Notebook: MNIST GANExcercise of GANGitHub
11The Complete ModelHints of the complete modelGitHub
12Generator & DiscriminatorGenerator and Discriminator Model implementationGitHub
13HyperparametersHyperparameters set for the excerciseGitHub
14Fake and Real LossesLoss calculation for the fake & real modelsGitHub
15Optimization Strategy, SolutionAdam optimization is used for D & G modelsGitHub
16Training Two NetworksComplete the training of the networksGitHub
17Training SolutionSolution of the training of the networksGitHub

Lesson-2: Deep Convolutional GANs

NoLessonTopicLink/Source
1Deep Convolutional GANsIntroduction about Deep convolutional GANsSource/GitHub
2DCGAN, DiscriminatorDCGAN Architecture basicSource/GitHub
3DCGAN GeneratorDCGAN Generator, transpose convolutional networkSource/GitHub
4What is Batch Normalization?Batch normalization defination and mathematical calculationSource/GitHub
5Pre-Notebook: Batch NormExcercise of Batch NormSource/GitHub
6Notebook: Batch NormExcercise of Batch NormSource/GitHub
7Benefits of Batch NormalizationDescribe the benefits of Batch NormalizationSource/GitHub
8DCGAN Notebook & DataDCGAN Excercise introductionSource/GitHub
9Pre-Notebook: DCGAN, SVHNExcercise of DCGAN, SVHNSource
10Notebook: DCGAN, SVHNExcercise of DCGAN, SVHNGitHub
11Scaling, SolutionScaling calculationGitHub
12DiscriminatorDiscriminator architecture for this networkGitHub
13Discriminator, SolutionDiscriminator architecture solution for this networkGitHub
14GeneratorDescribe the general structure of the generatorGitHub
15Generator, SolutionThe solution of the generator modelGitHub
16Optimization StrategyOptimization parameters set for the modelGitHub
17Optimization Solution & SamplesThe solution of Optimization parametersGitHub
18Other Applications of GANsMore about GAN - Semi-Supervised Learning, Domain Invariance, Ethical and Artistic Applications: Further ReadingSource/GitHub

Lesson-3: Pix2Pix & CycleGAN

NoLessonTopicLink/Source
1Introducing Jun-Yan ZhuIntroduction of Jun-Yan Zhu and his background, Intorduction CycleGAN, Pix2PixSource/GitHub
2Image to Image TranslationImage to image translation with exampleSource/GitHub
3Designing Loss FunctionsLoss are calculated using Euclidean distanceSource/GitHub
4GANs, a RecapFull review of Generator, Descrimenator of GAN networkGitHub
5Pix2Pix GeneratorWhat changes of Pix2Pix GeneratorSource/GitHub
6Pix2Pix DiscriminatorWhat changes of Pix2Pix DiscriminatorSource/GitHub
7CycleGANs & Unpaired DataUnpaired data, Mappings, Inverse mappingsSource/GitHub
8Cycle Consistency LossCalculate the Cycle Consistency LossSource/GitHub
9Why Does This Work?Weaknesses of CycleGANSource/GitHub
10Beyond CycleGANsAugmented CycleGAN, Paired CycleGAN, Cross-domain models, StarGANSource/GitHub

Lesson-4: Implementing a CycleGAN

NoLessonTopicLink/Source
1CycleGAN Notebook & DataIntroduction of the excercise, datasets, objective of the excerciseSource/GitHub
2Pre-Notebook: CycleGANCycleGAN ExcerciseSource
3Notebook: CycleGANExcercise of CycleGANGitHub
4DC DiscriminatorImplement the Discriminator FunctionGitHub
5DC Discriminator, SolutionSolution of the Discriminator FunctionGitHub
6Generator & Residual BlocksUses of Residual Blocks and it uses in the excerciseGitHub
7CycleGAN GeneratorImplement of Residual Blocks and Generator FunctionGitHub
8Blocks & Generator, SolutionSolution of Residual Blocks and Generator FunctionGitHub
9Adversarial & Cycle Consistency LossesDescription of Adversarial & Cycle Consistency LossesGitHub
10Loss & Optimization, SolutionSolution of Loss and optimizationGitHub
11Training ExerciseImplement the training function for descrimenator and generatorGitHub
12Training Solution & Generated SamplesIntroduction of the excercise, datasets, objective of the excerciseGitHub

6. Deploying a Model

Train and deploy your own PyTorch sentiment analysis model. Deployment gives you the ability to use a trained model to analyze new, user input. Build a model, deploy it, and create a gateway for accessing it from a website.

Lesson-1: Introduction to Deployment

NoLessonTopicLink/Source
1Welcome!Instructor introduction, deployment lesson introductionSource/GitHub
2What's AheadBehind the scenario of deployment, reason of using and it's characteristcsSource/GitHub
3Problem IntroductionHow to approach a real life problem using machine learningSource/GitHub
4Machine Learning WorkflowStructure of machine learning workflow with exampleSource/GitHub
5Machine Learning WorkflowMachine learning structure quizSource/GitHub
6What is Cloud Computing & WhyCloud computing defination, benfits, risks and now mostly why it is usedSource/GitHub
7Why Cloud Computing?Cloud computing quizSource/GitHub
8Machine Learning ApplicationsMachine Learning Applications, Example of ML in the workplaceSource/GitHub
9Machine Learning ApplicationsMachine Learning Applications, Example of ML in the workplaceSource/GitHub
10Paths to DeploymentPath of deployment, DevOps in Machine LearningSource/GitHub
11Paths to DeploymentPaths to Deployment quizSource/GitHub
12Production EnvironmentsProduction environments of ML and how it worksSource/GitHub
13Production EnvironmentsProduction Environments quizSource/GitHub
14Endpoints & REST APIsEndpoint and REST API description, HTTP communication and MethodSource/GitHub
15Endpoints & REST APIsEndpoints & REST APIs quizSource/GitHub
16ContainersContainer definition and structureSource/GitHub
17ContainersContainer QuizSource/GitHub
18Containers - Straight From the ExpertsContainer details from an expart developer - Jesse Swidler, a senior software engineer at UdacitySource/GitHub
19Characteristics of Modeling & DeploymentDescription of characteristics of Modeling & DeploymentSource/GitHub
20Characteristics of Modeling & DeploymentCharacteristics of Modeling & Deployment quizSource/GitHub
21Comparing Cloud ProvidersCharacteristics of Modeling & Deployment quizSource/GitHub
22Comparing Cloud ProvidersComparing Cloud Providers quizSource/GitHub
23Closing StatementsLearn about deploymentSource/GitHub
24SummarySummary of the lessonSource/GitHub
25[Optional] Cloud Computing DefinedDetails about cloud computing definedSource/GitHub
26[Optional] Cloud Computing ExplainedDetails about cloud computing definedSource/GitHub

Lesson-2: Building a Model using SageMaker

NoLessonTopicLink/Source
1Introduction to Amazon SageMakerBasic understanding of the SageMaker serviceSource/GitHub
2Create an AWS AccountProcedure to open an AWS accountSource/GitHub
3Checking GPU AccessChecking GPU AccessSource/GitHub
4Setting up a Notebook InstanceCreating an instance in Amazon SageMaker serviceSource/GitHub
5Cloning the Deployment NotebooksStarting instance and clone the project fileSource
6Is Everything Set Up?Setting up the AWS account and SageMaker instanceSource/GitHub
7Boston Housing Example - Getting the Data ReadyWorking with Boston Housing Example and Getting the Data ReadySource/GitHub
8Boston Housing Example - Training the ModelTraining XGBoost the modelSource/GitHub
9Boston Housing Example - Testing the ModelTest the model and clean up the data directorySource/GitHub
10Mini-Project: Building Your First ModelIntroduction the IMDB sentiment analysis mini projectSource
11Mini-Project: SolutionSolution of the mini projectSource/GitHub

Lesson-3: Deploying and Using a Model

Lesson-4: Hyperparameter Tuning

Lesson-5: Updating a Model

Project

Throughout this Nanodegree program, i'll have the opportunityto prove your skills by building the following projects-

1. Predicting Bike-Sharing Patterns

Build and train neural networks from scratch to predict the number of bikeshare users on a given day.

In this project, i was got to build a neural network from scratch to carry out a prediction problem on a real dataset.

The data comes from theUCI Machine Learning Database.

2. Dog-Breed Classifier

Design and train a convolutional neural network to analyze images of dogs and correctly identify their breeds. Use transfer learning and well-known architectures to improve this model - this is excellent preparation for more advanced applications.

3. Optimize Your GitHub Profile

GitHub Profiles are a key piece of "evidence" to an employer that you'd be a good job candidate, because they can see the details of your work. Recruiters use GitHub as a way to find job candidates, and many Nanodegree alumni have received work opportunities from their activity on GitHub. In addition, using GitHub is a way for you to collaborate on projects with other programmers - this will show that you are able to work well with others on an engineering team on the job.

4. Generate TV Scripts

Build a recurrent neural network on TensorFlow to process text. Use it to generate new episodes of your favorite TV show, based on old scripts.

5. Generate Faces

Build a pair of multi-layer neural networks and make them compete against each other in order to generate new, realistic faces. Try training them on a set of celebrity faces, and see what new faces the computer comes out with!

6. Improve your LinkedIn

7. Deploying a Sentiment Analysis Model

Train and deploy your own PyTorch sentiment analysis model. You'll build a model and create a gateway for accessing it from a website.

Extracurricular

1. Additional Lessons

Lesson-1: Evaluation Metrics

NoLessonTopicLink/Source
1IntroIntroduction about Evaluation MetricsSource/GitHub
2Confusion MatrixDescribed the model of confusion matrix and how it is usedSource/GitHub
3Confusion Matrix 2Quiz solution about confusion matrixSource/GitHub
4AccuracyImportance of accuracy in deep learning modelSource/GitHub
5Accuracy 2Quiz solution about accuracySource/GitHub
6When accuracy won't workIn some model accuracy is not play an vital role where accuracy impact bad resultsSource/GitHub
7False Negatives and PositivesDiscuss where the false negatives and positives is usedSource/GitHub
8Precision and RecallIntroduction about precision and recallSource/GitHub
9PrecisionDescribe the law of precision with examplesSource/GitHub
10RecallDescribe the law of recall with examplesSource/GitHub
10ROC CurveHow to calculate ROC Curve and graph of ROC CurveSource/GitHub

Lesson-2: Regression

NoLessonTopicLink/Source
1IntroIntroduction about Linear regression with examplesSource/GitHub
2Quiz: Housing PricesRegression example with housing pricesSource/GitHub
3Solution: Housing PricesSolution of regression problem of housing pricesSource/GitHub
4Fitting a Line Through DataHow to fit a line through dataSource/GitHub
5Moving a LineExplain how the line-slope work with graph & mathematicallySource/GitHub
6Absolute TrickHow to calculate the absolute trickSource/GitHub
7Square TrickAnother way to calculate come to the closer line calculationSource/GitHub
8Gradient DescentMinimize the errorSource/GitHub
9Mean Absolute ErrorLaw of mean absolute errorSource/GitHub
10Mean Squared ErrorLaw of mean squared errorSource/GitHub
11Minimizing Error FunctionsRelation in trick & error function and how minimize error functionSource/GitHub
12Mean vs Total ErrorDifference between Mean vs Total ErrorSource/GitHub
13Mini-batch Gradient DescentDefination of Mini-batch Gradient DescentSource/GitHub
14Absolute Error vs Squared ErrorDifferences between Absolute Error and Squared ErrorSource/GitHub
15Linear Regression in scikit-learnBasic sckit-learn and predict data using sklearn.linear_modelGitHub
16Higher DimensionsHigher dimensions error calculationSource/GitHub
17Multiple Linear RegressionMultiple Linear Regression with ExcerciseGitHub
18Closed Form SolutionHow to come closer in solution nth termSource/GitHub
19(Optional) Closed form Solution MathDerivation of error for nth term for closed form solutionGitHub
20Linear Regression WarningsWhere linear regression doesn't work wellGitHub
21Polynomial RegressionPolynomial Regression defination with one exampleSource/GitHub
22RegularizationL1 & L2 Regularization, Simple & Complex ModelSource/GitHub
23Neural Network RegressionBasic neural network for regressionSource/GitHub
24Neural Networks PlaygroundA Visual and Interactive Guide to the Basics of Neural NetworksSource/GitHub
25OutroEnding summurization of lessonSource/GitHub

Lesson-3: MiniFlow

NoLessonTopicLink/Source
1Welcome to MiniFlowLimitation of Numpy, introduction tensorflow, miniFlow and differentiable graphsSource/GitHub
2GraphsWhat is neural network and neural network graph, fordward propagatinSource/GitHub
3MiniFlow ArchitectureImplement the MiniFlow ArchitectureSource/GitHub
4Forward PropagationForward Propagation Implemented, Change the Add() functionGitHub
5Forward Propagation SolutionForward Propagation Solution with proper explainGitHub
6Learning and LossLinear neural network implementGitHub
7Linear TransformLinear Tranform functions are implementedGitHub
8Sigmoid FunctionWhere sigmoid function is implemented and how implementedGitHub
9CostLoss calculation using MSEGitHub
10Cost SolutionSolution of cost functionSource/GitHub
11Gradient DescentGradient Descent, Convergence, DivergenceGitHub
12BackpropagationHow to calculate backpropagation in the neural networkGitHub
13Stochastic Gradient DescentStochastic Gradient Descent ImpementationGitHub
14SGD SolutionStochastic Gradient Descent SolutionGitHub
15OutroEnding MessageSource/GitHub

2. TensorFlow, Keras, Frameworks

Lesson-1: Introduction to Keras

NoLessonTopicLink/Source
1IntroIntroductiona and lesson structure of kerasSource/GitHub
2KerasKeras usefull method details with excerciseGitHub
3Pre-Lab: Student Admissions in KerasExcercise implementation details describeSource/GitHub
4Lab: Student Admissions in KerasExcercise implementation details describeGitHub
5Optimizers in KerasDifferent types of keras optimizers detailsSource/GitHub
6Mini Project IntroHints the next coming mini projectSource/GitHub
7Pre-Lab: IMDB Data in KerasSolution TipsGitHub
8Lab: Student Admissions in KerasExcercise implementation details describeGitHub

Lesson-2: Keras CNNs

Lesson-3: Introduction to TensorFlow

30 Days of Udacity Challenge

The premise of this challenge is to build a habit of practicing new skills by making a public commitment of practicing the topic of your program every day for 30 days.

About

The course is contained knowledge that are useful to work on deep learning as an engineer. Simple neural networks & training, CNN, Autoencoders and feature extraction, Transfer learning, RNN, LSTM, NLP, Data augmentation, GANs, Hyperparameter tuning, Model deployment and serving are included in the course.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

[8]ページ先頭

©2009-2025 Movatter.jp