TensorFlow for Deep Learning Bootcamp
-
Introduction
-
Deep Learning and TensorFlow FundamentalsWhat is deep learning?0sWhy use deep learning?0sWhat are neural networks?0sPython + Machine Learning MonthlyWhat is deep learning already being used for?0sWhat is and why use TensorFlow?0sWhat is a Tensor?0sWhat we’re going to cover throughout the course0sHow to approach this course0sNeed A Refresher?Creating your first tensors with TensorFlow and tf.constant()0sCreating tensors with TensorFlow and tf.Variable()0sCreating random tensors with TensorFlow0sShuffling the order of tensors0sCreating tensors from NumPy arrays0sGetting information from your tensors (tensor attributes)0sIndexing and expanding tensors0sManipulating tensors with basic operations0sMatrix multiplication with tensors part 10sMatrix multiplication with tensors part 20sMatrix multiplication with tensors part 30sChanging the datatype of tensors0sTensor aggregation (finding the min, max, mean & more)0sTensor troubleshooting example (updating tensor datatypes)0sFinding the positional minimum and maximum of a tensor (argmin and argmax)0sSqueezing a tensor (removing all 1-dimension axes)0sOne-hot encoding tensors0sTrying out more tensor math operations0sExploring TensorFlow and NumPy’s compatibility0sMaking sure our tensor operations run really fast on GPUs0sTensorFlow Fundamentals challenge, exercises & extra-curriculumMonthly Coding Challenges, Free Resources and GuidesLinkedIn Endorsements
-
Neural network regression with TensorFlowIntroduction to Neural Network Regression with TensorFlow0sInputs and outputs of a neural network regression model0sAnatomy and architecture of a neural network regression model0sCreating sample regression data (so we can model it)0sNote: Code update for upcoming lecture(s) for TensorFlow 2.7.0+ fixThe major steps in modelling with TensorFlow0sSteps in improving a model with TensorFlow part 10sSteps in improving a model with TensorFlow part 20sSteps in improving a model with TensorFlow part 30sEvaluating a TensorFlow model part 1 (“visualise, visualise, visualise”)0sEvaluating a TensorFlow model part 2 (the three datasets)0sEvaluating a TensorFlow model part 3 (getting a model summary)0sEvaluating a TensorFlow model part 4 (visualising a model’s layers)0sEvaluating a TensorFlow model part 5 (visualising a model’s predictions)0sEvaluating a TensorFlow model part 6 (common regression evaluation metrics)0sEvaluating a TensorFlow regression model part 7 (mean absolute error)0sEvaluating a TensorFlow regression model part 7 (mean square error)0sSetting up TensorFlow modelling experiments part 1 (start with a simple model)0sSetting up TensorFlow modelling experiments part 2 (increasing complexity)0sComparing and tracking your TensorFlow modelling experiments0sHow to save a TensorFlow model0sHow to load and use a saved TensorFlow model0s(Optional) How to save and download files from Google Colab0sPutting together what we’ve learned part 1 (preparing a dataset)0sPutting together what we’ve learned part 2 (building a regression model)0sPutting together what we’ve learned part 3 (improving our regression model)0sPreprocessing data with feature scaling part 1 (what is feature scaling?)0sPreprocessing data with feature scaling part 2 (normalising our data)0sPreprocessing data with feature scaling part 3 (fitting a model on scaled data)0sTensorFlow Regression challenge, exercises & extra-curriculumLearning Guideline
-
Neural network classification in TensorFlowIntroduction to neural network classification in TensorFlow0sExample classification problems (and their inputs and outputs)0sInput and output tensors of classification problems0sTypical architecture of neural network classification models with TensorFlow0sCreating and viewing classification data to model0sChecking the input and output shapes of our classification data0sBuilding a not very good classification model with TensorFlow0sTrying to improve our not very good classification model0sCreating a function to view our model’s not so good predictions0sNote: Updates for TensorFlow 2.7.0Make our poor classification model work for a regression dataset0sNon-linearity part 1: Straight lines and non-straight lines0sNon-linearity part 2: Building our first neural network with non-linearity0sNon-linearity part 3: Upgrading our non-linear model with more layers0sNon-linearity part 4: Modelling our non-linear data once and for all0sNon-linearity part 5: Replicating non-linear activation functions from scratch0sGetting great results in less time by tweaking the learning rate0sUsing the TensorFlow History object to plot a model’s loss curves0sUsing callbacks to find a model’s ideal learning rate0sTraining and evaluating a model with an ideal learning rate0sIntroducing more classification evaluation methods0sFinding the accuracy of our classification model0sCreating our first confusion matrix (to see where our model is getting confused)0sMaking our confusion matrix prettier0sPutting things together with multi-class classification part 1: Getting the data0sMulti-class classification part 2: Becoming one with the data0sMulti-class classification part 3: Building a multi-class classification model0sMulti-class classification part 4: Improving performance with normalisation0sMulti-class classification part 5: Comparing normalised and non-normalised data0sMulti-class classification part 6: Finding the ideal learning rate0sMulti-class classification part 7: Evaluating our model0sMulti-class classification part 8: Creating a confusion matrix0sMulti-class classification part 9: Visualising random model predictions0sWhat “patterns” is our model learning?0sTensorFlow classification challenge, exercises & extra-curriculum
-
Computer Vision and Convolutional Neural Networks in TensorFlowIntroduction to Computer Vision with TensorFlow0sIntroduction to Convolutional Neural Networks (CNNs) with TensorFlow0sDownloading an image dataset for our first Food Vision model0sBecoming One With Data0sBecoming One With Data Part 20sBecoming One With Data Part 30sBuilding an end to end CNN Model0sUsing a GPU to run our CNN model 5x faster0sTrying a non-CNN model on our image data0sImproving our non-CNN model by adding more layers0sBreaking our CNN model down part 1: Becoming one with the data0sBreaking our CNN model down part 2: Preparing to load our data0sBreaking our CNN model down part 3: Loading our data with ImageDataGenerator0sBreaking our CNN model down part 4: Building a baseline CNN model0sBreaking our CNN model down part 5: Looking inside a Conv2D layer0sBreaking our CNN model down part 6: Compiling and fitting our baseline CNN0sBreaking our CNN model down part 7: Evaluating our CNN’s training curves0sBreaking our CNN model down part 8: Reducing overfitting with Max Pooling0sBreaking our CNN model down part 9: Reducing overfitting with data augmentation0sBreaking our CNN model down part 10: Visualizing our augmented data0sBreaking our CNN model down part 11: Training a CNN model on augmented data0sBreaking our CNN model down part 12: Discovering the power of shuffling data0sBreaking our CNN model down part 13: Exploring options to improve our model0sDownloading a custom image to make predictions on0sWriting a helper function to load and preprocessing custom images0sMaking a prediction on a custom image with our trained CNN0sMulti-class CNN’s part 1: Becoming one with the data0sMulti-class CNN’s part 2: Preparing our data (turning it into tensors)0sMulti-class CNN’s part 3: Building a multi-class CNN model0sMulti-class CNN’s part 4: Fitting a multi-class CNN model to the data0sMulti-class CNN’s part 5: Evaluating our multi-class CNN model0sMulti-class CNN’s part 6: Trying to fix overfitting by removing layers0sMulti-class CNN’s part 7: Trying to fix overfitting with data augmentation0sMulti-class CNN’s part 8: Things you could do to improve your CNN model0sMulti-class CNN’s part 9: Making predictions with our model on custom images0sSaving and loading our trained CNN model0sTensorFlow computer vision and CNNs challenge, exercises & extra-curriculum
-
Transfer Learning in TensorFlow Part 1: Feature extractionWhat is and why use transfer learning?0sDownloading and preparing data for our first transfer learning model0sIntroducing Callbacks in TensorFlow and making a callback to track our models0sExploring the TensorFlow Hub website for pretrained models0sBuilding and compiling a TensorFlow Hub feature extraction model0sBlowing our previous models out of the water with transfer learning0sPlotting the loss curves of our ResNet feature extraction model0sBuilding and training a pre-trained EfficientNet model on our data0sDifferent Types of Transfer Learning0sComparing Our Model’s Results0sTensorFlow Transfer Learning Part 1 challenge, exercises & extra-curriculum
-
Transfer Learning in TensorFlow Part 2: Fine tuningIntroduction to Transfer Learning in TensorFlow Part 2: Fine-tuning0sImporting a script full of helper functions (and saving lots of space)0sDownloading and turning our images into a TensorFlow BatchDataset0sDiscussing the four (actually five) modelling experiments we’re running0sComparing the TensorFlow Keras Sequential API versus the Functional API0sNote: Fixes for EfficientNetB0 model creation + weight loadingCreating our first model with the TensorFlow Keras Functional API0sCompiling and fitting our first Functional API model0sGetting a feature vector from our trained model0sDrilling into the concept of a feature vector (a learned representation)0sDownloading and preparing the data for Model 1 (1 percent of training data)0sBuilding a data augmentation layer to use inside our model0sNote: Small fix for next video, for images not augmentingVisualizing what happens when images pass through our data augmentation layer0sBuilding Model 1 (with a data augmentation layer and 1% of training data)0sBuilding Model 2 (with a data augmentation layer and 10% of training data)0sCreating a ModelCheckpoint to save our model’s weights during training0sFitting and evaluating Model 2 (and saving its weights using ModelCheckpoint)0sLoading and comparing saved weights to our existing trained Model 20sPreparing Model 3 (our first fine-tuned model)0sFitting and evaluating Model 3 (our first fine-tuned model)0sComparing our model’s results before and after fine-tuning0sDownloading and preparing data for our biggest experiment yet (Model 4)0sPreparing our final modelling experiment (Model 4)0sFine-tuning Model 4 on 100% of the training data and evaluating its results0sComparing our modelling experiment results in TensorBoard0sHow to view and delete previous TensorBoard experiments0sTransfer Learning in TensorFlow Part 2 challenge, exercises and extra-curriculum
-
Transfer Learning with TensorFlow Part 3: Scaling UpIntroduction to Transfer Learning Part 3: Scaling Up0sGetting helper functions ready and downloading data to model0sOutlining the model we’re going to build and building a ModelCheckpoint callback0sCreating a data augmentation layer to use with our model0sCreating a headless EfficientNetB0 model with data augmentation built in0sFitting and evaluating our biggest transfer learning model yet0sUnfreezing some layers in our base model to prepare for fine-tuning0sFine-tuning our feature extraction model and evaluating its performance0sSaving and loading our trained model0sDownloading a pretrained model to make and evaluate predictions with0sMaking predictions with our trained model on 25,250 test samples0sUnravelling our test dataset for comparing ground truth labels to predictions0sConfirming our model’s predictions are in the same order as the test labels0sCreating a confusion matrix for our model’s 101 different classes0sEvaluating every individual class in our dataset0sPlotting our model’s F1-scores for each separate class0sCreating a function to load and prepare images for making predictions0sMaking predictions on our test images and evaluating them0sDiscussing the benefits of finding your model’s most wrong predictions0sWriting code to uncover our model’s most wrong predictions0sPlotting and visualising the samples our model got most wrong0sMaking predictions on and plotting our own custom images0sTransfer Learning in TensorFlow Part 3 challenge, exercises and extra-curriculum
-
Milestone Project 1: Food Vision Big™Introduction to Milestone Project 1: Food Vision Big™0sMaking sure we have access to the right GPU for mixed precision training0sGetting helper functions ready0sIntroduction to TensorFlow Datasets (TFDS)0sExploring and becoming one with the data (Food101 from TensorFlow Datasets)0sCreating a preprocessing function to prepare our data for modelling0sBatching and preparing our datasets (to make them run fast)0sExploring what happens when we batch and prefetch our data0sCreating modelling callbacks for our feature extraction model0sNote: Mixed Precision producing errors for TensorFlow 2.5+Turning on mixed precision training with TensorFlow0sCreating a feature extraction model capable of using mixed precision training0sChecking to see if our model is using mixed precision training layer by layer0sTraining and evaluating a feature extraction model (Food Vision Big™)0sIntroducing your Milestone Project 1 challenge: build a model to beat DeepFood0sMilestone Project 1: Food Vision Big™, exercises and extra-curriculum
-
NLP Fundamentals in TensorFlowWelcome to natural language processing with TensorFlow!Introduction to Natural Language Processing (NLP) and Sequence Problems0sExample NLP inputs and outputs0sThe typical architecture of a Recurrent Neural Network (RNN)0sPreparing a notebook for our first NLP with TensorFlow project0sBecoming one with the data and visualising a text dataset0sSplitting data into training and validation sets0sConverting text data to numbers using tokenisation and embeddings (overview)0sSetting up a TensorFlow TextVectorization layer to convert text to numbers0sMapping the TextVectorization layer to text data and turning it into numbers0sCreating an Embedding layer to turn tokenised text into embedding vectors0sDiscussing the various modelling experiments we’re going to run0sModel 0: Building a baseline model to try and improve upon0sCreating a function to track and evaluate our model’s results0sModel 1: Building, fitting and evaluating our first deep model on text data0sVisualising our model’s learned word embeddings with TensorFlow’s projector tool0sHigh-level overview of Recurrent Neural Networks (RNNs) + where to learn more0sModel 2: Building, fitting and evaluating our first TensorFlow RNN model (LSTM)0sModel 3: Building, fitting and evaluating a GRU-cell powered RNN0sModel 4: Building, fitting and evaluating a bidirectional RNN model0sDiscussing the intuition behind Conv1D neural networks for text and sequences0sModel 5: Building, fitting and evaluating a 1D CNN for text0sUsing TensorFlow Hub for pretrained word embeddings (transfer learning for NLP)0sModel 6: Building, training and evaluating a transfer learning model for NLP0sPreparing subsets of data for model 7 (same as model 6 but 10% of data)0sModel 7: Building, training and evaluating a transfer learning model on 10% data0sFixing our data leakage issue with model 7 and retraining it0sComparing all our modelling experiments evaluation metrics0sUploading our model’s training logs to TensorBoard and comparing them0sSaving and loading in a trained NLP model with TensorFlow0sDownloading a pretrained model and preparing data to investigate predictions0sVisualising our model’s most wrong predictions0sMaking and visualising predictions on the test dataset0sUnderstanding the concept of the speed/score tradeoff0sNLP Fundamentals in TensorFlow challenge, exercises and extra-curriculum
-
Milestone Project 2: SkimLitIntroduction to Milestone Project 2: SkimLit0sWhat we’re going to cover in Milestone Project 2 (NLP for medical abstracts)0sSkimLit inputs and outputs0sSetting up our notebook for Milestone Project 2 (getting the data)0sVisualising examples from the dataset (becoming one with the data)0sWriting a preprocessing function to structure our data for modelling0sPerforming visual data analysis on our preprocessed text0sTurning our target labels into numbers (ML models require numbers)0sModel 0: Creating, fitting and evaluating a baseline model for SkimLit0sPreparing our data for deep sequence models0sCreating a text vectoriser to map our tokens (text) to numbers0sCreating a custom token embedding layer with TensorFlow0sCreating fast loading dataset with the TensorFlow tf.data API0sModel 1: Building, fitting and evaluating a Conv1D with token embeddings0sPreparing a pretrained embedding layer from TensorFlow Hub for Model 20sModel 2: Building, fitting and evaluating a Conv1D model with token embeddings0sCreating a character-level tokeniser with TensorFlow’s TextVectorization layer0sCreating a character-level embedding layer with tf.keras.layers.Embedding0sModel 3: Building, fitting and evaluating a Conv1D model on character embeddings0sDiscussing how we’re going to build Model 4 (character + token embeddings)0sModel 4: Building a multi-input model (hybrid token + character embeddings)0sModel 4: Plotting and visually exploring different data inputs0sCrafting multi-input fast loading tf.data datasets for Model 40sModel 4: Building, fitting and evaluating a hybrid embedding model0sModel 5: Adding positional embeddings via feature engineering (overview)0sEncoding the line number feature to used with Model 50sEncoding the total lines feature to be used with Model 50sModel 5: Building the foundations of a tribrid embedding model0sModel 5: Completing the build of a tribrid embedding model for sequences0sVisually inspecting the architecture of our tribrid embedding model0sCreating multi-level data input pipelines for Model 5 with the tf.data API0sBringing SkimLit to life!!! (fitting and evaluating Model 5)0sComparing the performance of all of our modelling experiments0sSaving, loading & testing our best performing model0sCongratulations and your challenge before heading to the next module0sMilestone Project 2 (SkimLit) challenge, exercises and extra-curriculum
-
Time Series fundamentals in TensorFlow + Milestone Project 3: BitPredictWelcome to time series fundamentals with TensorFlow + Milestone Project 3!Introduction to Milestone Project 3 (BitPredict) & where you can get help0sWhat is a time series problem and example forecasting problems at Uber0sExample forecasting problems in daily life0sWhat can be forecast?0sWhat we’re going to cover (broadly)0sTime series forecasting inputs and outputs0sDownloading and inspecting our Bitcoin historical dataset0sDifferent kinds of time series patterns & different amounts of feature variables0sVisualizing our Bitcoin historical data with pandas0sReading in our Bitcoin data with Python’s CSV module0sCreating train and test splits for time series (the wrong way)0sCreating train and test splits for time series (the right way)0sCreating a plotting function to visualize our time series data0sDiscussing the various modelling experiments were going to be running0sModel 0: Making and visualizing a naive forecast model0sDiscussing some of the most common time series evaluation metrics0sImplementing MASE with TensorFlow0sCreating a function to evaluate our model’s forecasts with various metrics0sDiscussing other non-TensorFlow kinds of time series forecasting models0sFormatting data Part 2: Creating a function to label our windowed time series0sDiscussing the use of windows and horizons in time series data0sWriting a preprocessing function to turn time series data into windows & labels0sTurning our windowed time series data into training and test sets0sCreating a modelling checkpoint callback to save our best performing model0sModel 1: Building, compiling and fitting a deep learning model on Bitcoin data0sCreating a function to make predictions with our trained models0sModel 2: Building, fitting and evaluating a deep model with a larger window size0sModel 3: Building, fitting and evaluating a model with a larger horizon size0sAdjusting the evaluation function to work for predictions with larger horizons0sModel 3: Visualizing the results0sComparing our modelling experiments so far and discussing autocorrelation0sPreparing data for building a Conv1D model0sModel 4: Building, fitting and evaluating a Conv1D model on our Bitcoin data0sModel 5: Building, fitting and evaluating a LSTM (RNN) model on our Bitcoin data0sInvestigating how to turn our univariate time series into multivariate0sCreating and plotting a multivariate time series with BTC price and block reward0sPreparing our multivariate time series for a model0sModel 6: Building, fitting and evaluating a multivariate time series model0sModel 7: Discussing what we’re going to be doing with the N-BEATS algorithm0sModel 7: Replicating the N-BEATS basic block with TensorFlow layer subclassing0sModel 7: Testing our N-BEATS block implementation with dummy data inputs0sModel 7: Creating a performant data pipeline for the N-BEATS model with tf.data0sModel 7: Setting up hyperparameters for the N-BEATS algorithm0sModel 7: Getting ready for residual connections0sModel 7: Outlining the steps we’re going to take to build the N-BEATS model0sModel 7: Putting together the pieces of the puzzle of the N-BEATS model0sModel 7: Plotting the N-BEATS algorithm we’ve created and admiring its beauty0sModel 8: Ensemble model overview0sModel 8: Building, compiling and fitting an ensemble of models0sModel 8: Making and evaluating predictions with our ensemble model0sDiscussing the importance of prediction intervals in forecasting0sGetting the upper and lower bounds of our prediction intervals0sPlotting the prediction intervals of our ensemble model predictions0s(Optional) Discussing the types of uncertainty in machine learning0sModel 9: Preparing data to create a model capable of predicting into the future0sModel 9: Building, compiling and fitting a future predictions model0sModel 9: Discussing what’s required for our model to make future predictions0sModel 9: Creating a function to make forecasts into the future0sModel 9: Plotting our model’s future forecasts0sModel 10: Introducing the turkey problem and making data for it0sModel 10: Building a model to predict on turkey data (why forecasting is BS)0sComparing the results of all of our models and discussing where to go next0sTensorFlow Time Series Fundamentals Challenge and Extra Resources
-
Where To Go From Here?
-
Appendix: Machine Learning PrimerQuick Note: Upcoming VideosWhat is Machine Learning?0sAI/Machine Learning/Data Science0sExercise: Machine Learning Playground0sHow Did We Get Here?0sExercise: YouTube Recommendation Engine0sTypes of Machine Learning0sAre You Getting It Yet?What Is Machine Learning? Round 20sSection Review0s
-
Appendix: Machine Learning and Data Science FrameworkQuick Note: Upcoming VideosSection Overview0sIntroducing Our Framework0s6 Step Machine Learning Framework0sTypes of Machine Learning Problems0sTypes of Data0sTypes of Evaluation0sFeatures In Data0sModelling – Splitting Data0sModelling – Picking the Model0sModelling – Tuning0sModelling – Comparison0sOverfitting and Underfitting DefinitionsExperimentation0sTools We Will Use0sOptional: Elements of AI
-
Appendix: Pandas for Data AnalysisQuick Note: Upcoming VideosSection Overview0sDownloading Workbooks and AssignmentsPandas Introduction0sSeries, Data Frames and CSVs0sData from URLsDescribing Data with Pandas0sSelecting and Viewing Data with Pandas0sSelecting and Viewing Data with Pandas Part 20sManipulating Data0sManipulating Data 20sManipulating Data 30sAssignment: Pandas PracticeHow To Download The Course Assignments0s
-
Appendix: NumPyQuick Note: Upcoming VideosSection Overview0sNumPy Introduction0sQuick Note: Correction In Next VideoNumPy DataTypes and Attributes0sCreating NumPy Arrays0sNumPy Random Seed0sViewing Arrays and Matrices0sManipulating Arrays0sManipulating Arrays 20sStandard Deviation and Variance0sReshape and Transpose0sDot Product vs Element Wise0sExercise: Nut Butter Store Sales0sComparison Operators0sSorting Arrays0sTurn Images Into NumPy Arrays0sAssignment: NumPy PracticeOptional: Extra NumPy resources
-
Thanks
Just launched with all modern best practices for building neural networks with TensorFlow and becoming a TensorFlow & Deep Learning Expert!
Join a live online community of over 900,000+ students and a course taught by a TensorFlow expert. This course will take you from absolute beginner with TensorFlow, to creating state-of-the-art deep learning neural networks.
TensorFlow experts earn up to $204,000 USD a year, with the average salary hovering around $148,000 USD. By taking this course you will be joining the growing Machine Learning industry and becoming a top paid TensorFlow Developer!
Here is a full course breakdown of everything we will teach (yes, it’s very comprehensive, but don’t be intimidated, as we will teach you everything from scratch!):
The goal of this course is to teach you all the skills necessary for you to become a top 10% TensorFlow Developer.
This course will be very hands on and project based. You won’t just be staring at us teach, but you will actually get to experiment, do exercises, and build machine learning models and projects to mimic real life scenarios. By the end of it all, you will develop skillsets needed to develop modern deep learning solutions that big tech companies encounter.
0 — TensorFlow Fundamentals
Introduction to tensors (creating tensors)
Getting information from tensors (tensor attributes)
Manipulating tensors (tensor operations)
Tensors and NumPy
Using @tf.function (a way to speed up your regular Python functions)
Using GPUs with TensorFlow
1 — Neural Network Regression with TensorFlow
Build TensorFlow sequential models with multiple layers
Prepare data for use with a machine learning model
Learn the different components which make up a deep learning model (loss function, architecture, optimization function)
Learn how to diagnose a regression problem (predicting a number) and build a neural network for it
2 — Neural Network Classification with TensorFlow
Learn how to diagnose a classification problem (predicting whether something is one thing or another)
Build, compile & train machine learning classification models using TensorFlow
Build and train models for binary and multi-class classification
Plot modelling performance metrics against each other
Match input (training data shape) and output shapes (prediction data target)
3 — Computer Vision and Convolutional Neural Networks with TensorFlow
Build convolutional neural networks with Conv2D and pooling layers
Learn how to diagnose different kinds of computer vision problems
Learn to how to build computer vision neural networks
Learn how to use real-world images with your computer vision models
4 — Transfer Learning with TensorFlow Part 1: Feature Extraction
Learn how to use pre-trained models to extract features from your own data
Learn how to use TensorFlow Hub for pre-trained models
Learn how to use TensorBoard to compare the performance of several different models
5 — Transfer Learning with TensorFlow Part 2: Fine-tuning
Learn how to setup and run several machine learning experiments
Learn how to use data augmentation to increase the diversity of your training data
Learn how to fine-tune a pre-trained model to your own custom problem
Learn how to use Callbacks to add functionality to your model during training
6 — Transfer Learning with TensorFlow Part 3: Scaling Up (Food Vision mini)
Learn how to scale up an existing model
Learn to how evaluate your machine learning models by finding the most wrong predictions
Beat the original Food101 paper using only 10% of the data
7 — Milestone Project 1: Food Vision
Combine everything you’ve learned in the previous 6 notebooks to build Food Vision: a computer vision model able to classify 101 different kinds of foods. Our model well and truly beats the original Food101 paper.
8 — NLP Fundamentals in TensorFlow
Learn to:
Preprocess natural language text to be used with a neural network
Create word embeddings (numerical representations of text) with TensorFlow
Build neural networks capable of binary and multi-class classification using:
RNNs (recurrent neural networks)
LSTMs (long short-term memory cells)
GRUs (gated recurrent units)
CNNs
Learn how to evaluate your NLP models
9 — Milestone Project 2: SkimLit
Replicate a the model which powers the PubMed 200k paper to classify different sequences in PubMed medical abstracts (which can help researchers read through medical abstracts faster)
10 — Time Series fundamentals in TensorFlow
Learn how to diagnose a time series problem (building a model to make predictions based on data across time, e.g. predicting the stock price of AAPL tomorrow)
Prepare data for time series neural networks (features and labels)
Understanding and using different time series evaluation methods
MAE — mean absolute error
Build time series forecasting models with TensorFlow
RNNs (recurrent neural networks)
CNNs (convolutional neural networks)
11 — Milestone Project 3: (Surprise)
If you’ve read this far, you are probably interested in the course. This last project will be good… we promise you, so see you inside the course 😉
TensorFlow is growing in popularity and more and more job openings are appearing for this specialized knowledge. As a matter of fact, TensorFlow is outgrowing other popular ML tools like PyTorch in job market. Google, Airbnb, Uber, DeepMind, Intel, IBM, Twitter, and many others are currently powered by TensorFlow. There is a reason these big tech companies are using this technology and you will find out all about the power that TensorFlow gives developers.
We guarantee you this is the most comprehensive online course on TensorFlow. So why wait? Make yourself stand out by becoming a TensorFlow Expert and advance your career.
See you inside the course!
What's included
- 62.5 hours on-demand video
- 41 articles
- 5 downloadable resources
- Access on mobile and TV
- Certificate of completion