Data PRO or Pay-Per-Course

Pick a plan that right's for you!

Pay per course or a flat monthly subscription with no contracts. Become a Data PRO and get access to all data engineering, programming and data science courses.
Explore Data PRO

Course curriculum

  • 1
    Introduction
  • 2
    Installation
  • 3
    TensorFlow and Machine Learning
  • 4
    Working with Images
  • 5
    K-Nearest-Neighbors with TensorFlow
  • 6
    Linear Regression with a Single Neuron
  • 7
    Linear Regression in TensorFlow
  • 8
    Logistic Regression in TensorFlow
  • 9
    The Estimator API
  • 10
    Neural Networks and Deep Learning
  • 11
    Classifiers and Classification
  • 12
    Convolutional Neural Networks (CNNs)
  • 13
    Recurrent Neural Networks (RNNs)
  • 14
    Unsupervised Learning
  • 15
    TensorFlow on the Google Cloud
  • 16
    TensorFlow Using Cloud ML Engine
  • 17
    Feature Engineering and Hyperparameter Tuning
  • You, This Course and Us Source Code and PDFs Datasets for all Labs Downloads
  • Install TensorFlow Install Jupyter Notebook Running on the GCP vs. Running on your local machine Lab: Setting Up A GCP Account Lab: Using The Cloud Shell Datalab ~ Jupyter Lab: Creating And Working On A Datalab Instance Downloads
  • Introducing Machine Learning Representation Learning Neural Networks Introduced Introducing TensorFlow Running on the GCP vs. Running on your local machine Lab: Simple Math Operations Computation Graph Tensors Lab: Tensors Linear Regression Intro Placeholders and Variables Lab: Placeholders Lab: Variables Lab: Linear Regression with Made-up Data
  • Image Processing Images As Tensors Lab: Reading and Working with Images Lab: Image Transformations
  • Introducing MNIST K-Nearest Neigbors One-hot Notation and L1 Distance Steps in the K-Nearest-Neighbors Implementation Lab: K-Nearest-Neighbors
  • Learning Algorithm Individual Neuron Learning Regression Learning XOR XOR Trained
  • Lab: Access Data from Yahoo Finance Non TensorFlow Regression Lab: Linear Regression - Setting Up a Baseline Gradient Descent Lab: Linear Regression Lab: Multiple Regression in TensorFlow
  • Logistic Regression Introduced Linear Classification Lab: Logistic Regression - Setting Up a Baseline Logit Softmax Argmax Lab: Logistic Regression
  • Estimators Lab: Linear Regression using Estimators Lab: Logistic Regression using Estimators
  • Traditional Machine Learning Deep Learning Operation of a Single Neuron The Activation Function Training a Neural Network: Back Propagation Lab: Automobile Price Prediction - Exploring the Dataset Lab: Automobile Price Prediction - Using TensorFlow for Prediction Hyperparameters Vanishing and Exploding Gradients The Bias-Variance Trade-off Preventing Overfitting Lab: Iris Flower Classification
  • Classification as an ML Problem Confusion Matrix: Accuracy, Precision and Recall Confusion Matrix: Accuracy, Precision and Recall F1 Scores and The ROC Curve
  • Mimicking the Visual Cortex Convolution Choice of Kernel Functions Zero Padding and Stride Size CNNs vs DNNs Feature Maps Pooling Lab: Classification of Street View House Numbers - Exploring the Dataset Basic Architecture of a CNN Lab: Classification of Street View House Numbers - Building the Model Lab: Classification of Street View House Numbers - Running the Model Lab: Building a CNN Using the Estimator API
  • Learning From the Past Unrolling an RNN Cell Through Time Training an RNN - Back Propagation Through Time Lab: RNNs for Image Classifcation Vanishing and Exploding Gradients in an RNN Long Memory Neurons vs Truncated BPTT The Long/Short Term Memory Cell A Sequence of Words Text in Numeric Form Lab: Sentiment Analysis on Rotten Tomatoes Reviews - Exploring the Dataset Lab: Sentiment Analysis on Rotten Tomatoes Reviews - Building, Running the Model
  • Supervised and Unsupervised Learning Expressing Attributes as Numbers K-Means Clustering Lab: K-Means Clustering with 2-Dimensional Points in Space Lab: K-Means Clustering with Images Patterns in Data Principal Components Analysis Autoencoders Autoencoder Neural Network Architecture Lab: PCA on Stock Data - Matplotlib vs Autoencoders Stacked Autoencoders Lab: Stacked Autoencoder With Dropout Lab: Stacked Autoencoder With Regularization and He Initialization Denoising Autoencoders Lab: Denoising Autoencoder with Gaussian Noise
  • Running TensorFlow on the Cloud Lab: Taxicab Prediction - Setting up the dataset Lab: Taxicab Prediction - Training and Running the model Downloads
  • A Taxicab Fare Prediction Problem Datalab Querying BigQuery Explore Data Clean Data Benchmark Using TensorFlow The Estimator API The Experiment Function Introduction to Cloud MLE Using Cloud MLE The Training Service The Prediction Service
  • Feature Engineering to the rescue New Approach Dataflow Create Pipeline Dataflow Run Pipeline Feature Engineering Deep And Wide Models Hyperparameter Tuning Hyperparameter Tuning on the GCP

Course Description

What will I learn?

  • Build and execute machine learning models on TensorFlow
  • Implement Deep Neural Networks, Convolutional Neural Networks and Recurrent Neural Networks
  • Understand and implement unsupervised learning models such as Clustering and Autoencoders


About the course

TensorFlow is quickly becoming the technology of choice for deep learning, because of how easy TF makes it to build powerful and sophisticated neural networks. The Google Cloud Platform is a great place to run TF models at scale, and perform distributed training and prediction.

This is a comprehensive, from-the-basics course on TensorFlow and building neural networks. It assumes no prior knowledge of Tensorflow, all you need to know is basic Python programming.


What's covered: 

  • Deep learning basics: What a neuron is; how neural networks connect neurons to 'learn' complex functions; how TF makes it easy to build neural network models
  • Using Deep Learning for the famous ML problems: regression, classification, clustering and autoencoding
  • CNNs - Convolutional Neural Networks: Kernel functions, feature maps, CNNs v DNNs 
  • RNNs - Recurrent Neural Networks: LSTMs, Back-propagation through time and dealing with vanishing/exploding gradients
  • Unsupervised learning techniques - Autoencoding, K-means clustering, PCA as autoencoding 
  • Working with images
  • Working with documents and word embeddings
  • Google Cloud ML Engine: Distributed training and prediction of TF models on the cloud
  • Working with TensorFlow estimators


Who should take the course?

  • Developers who want to understand and build ML and deep learning models in TensorFlow
  • Data scientists who want to learn cutting edge TensorFlow technology


Pre-requisites & Requirements

  • Basic proficiency at programming in Python
  • Basic understanding of machine learning models is useful but not required