Skip to content

Latest commit

 

History

History
111 lines (81 loc) · 5.74 KB

checklist.md

File metadata and controls

111 lines (81 loc) · 5.74 KB

TensorFlow Developer Certification Exam Requirements

source: https://www.notion.so/Getting-TensorFlow-Developer-Certified-Curriculum-ff8385b6f9284fdfbc930ea06ce8749c

Read the following two handbooks multiple times before the exam.

Criteria (taken from TensorFlow Candidate Handbook)

The exam tests students in their ability to solve problems by building models using TensorFlow 2.x.

Skills checklist

(1) Build and train neural network models using TensorFlow 2.x

Best resources (see above for links):

  • Part 1 of the TensorFlow in Practice Specialization
  • Chapters 10, 11, 12, 13 of the Hands-on Machine Learning Book (2nd edition)
  • MIT Intro to Deep Learning Lecture 1

You need to understand the foundational principles of machine learning (ML) and deep learning (DL) using TensorFlow 2.x. You need to know how to:

  • Use TensorFlow 2.x.
  • Build, compile and train machine learning (ML) models using TensorFlow.
  • Preprocess data to get it read for use in a model.
  • Use the models to predict results.
  • Build sequential models with multiple layers.
  • Build and train models for binary classification.
  • Build and train models for multi-class classification.
  • Plot loss and accuracy of a trained model.
  • Identify strategies to prevent overfitting, including augmentation and dropout.
  • Use pretrained models (transfer learning).
  • Extract features from pre-trained models.
  • Ensure that inputs to a model are in the correct shape.
  • Ensure that you can match test data to the input shape of a neural network.
  • Ensure you can match output data of a neural network to specified input shape for test data.
  • Understand batch loading of data.
  • Use callbacks to trigger the end of training cycles.
  • Use datasets from different sources.
  • Use datasets in different formats, including json and csv.
  • Use datasets from tf.data.datasets.

(2) Image classification

Best resources (see above for links):

  • Part 2 of the TensorFlow in Practice Specialization
  • Chapter 14 of the Hands-on Machine Learning Book (2nd edition)
  • MIT Intro to Deep Learning Lecture 3

You need to understand how to build image recognition and object detection models with deep neural networks and convolutional neural networks using TensorFlow 2.x. You need to know how to:

  • Define Convolutional neural networks with Conv2D and pooling layers.
  • Build and train models to process real-world image datasets.
  • Understand how to use convolutions to improve your neural network.
  • Use real-world images in different shapes and sizes.
  • Use image augmentation to prevent overfitting.
  • Use ImageDataGenerator.
  • Understand how ImageDataGenerator labels images based on the directory structure.

(3) Natural language processing (NLP)

Best resources (see above for links):

  • Part 3 of the TensorFlow in Practice Specialization
  • Chapter 16 of the Hands-on Machine Learning Book (2nd edition)
  • MIT Intro to Deep Learning Lecture 2

You need to understand how to use neural networks to solve natural language preprocessing problems using TensorFlow. You need to know how to:

  • Build natural language processing systems using TensorFlow.
  • Prepare text to use in TensorFlow models.
  • Build models that identify the category of a piece of text using binary classification.
  • Build models that identify the category of a piece of test using multi-class categorization.
  • Use word embeddings in your TensorFlow model.
  • Use LSTMs in your model to classify text for either binary or multi-class categorization.
  • Add RNN and GRU layers to your model.
  • Use RNNs, LSTMs, GRUs and CNNs in models that work with text.
  • Train LSTMs on existing test to generate text (such as songs and poetry).

(4) Time series, sequences and predictions

Best resources (see above for links):

  • Part 4 of the TensorFlow in Practice Specialization
  • Chapter 15 of the Hands-on Machine Learning Book (2nd edition)
  • MIT Intro to Deep Learning Lecture 2

You need to understand how to solve time series and forecasting problems in TensorFlow. You need to know how to:

  • Train, tune and use time series, sequence and prediction models.
  • Prepare data for time series learning.
  • Understand Mean Average Error (MAE) and how it can be used to evaluate the accuracy of sequence models.
  • Use RNNs and CNNs for time series, sequence and forecasting models.
  • Identify when to use trailing versus centred windows.
  • Use TensorFlow for forecasting.
  • Prepare features and labels.
  • Identify and compensate for sequence bias.
  • Adjust the learning rate dynamically in time series, sequence and prediction models.

Resources allowed

You may use whatever learning resources you would learning use during your ML development work.

Exam environment

You take the exam through the PyCharm IDE and a TensorFlow Exam plugin. I will look into this the closer I get to the exam. For now, time to study and prepare.

To get familiar with PyCharm, go through the PyCharm getting started series.