TensorFlow Newsletter June 2023
Explore new tools, use LLMs in real-world applications, and more
|
Learn how Keras makes deep learning easy
|
|
Explore the components of the Keras API, which provides an approachable interface for solving machine learning problems with TensorFlow.
|
|
|
|
|
|
|
|
Create an autocomplete Android app with KerasNLP and TensorFlow Lite
|
Large language models (LLMs) are trained to generate text based on large datasets. Learn how to load a KerasNLP model, optimize it with quantization techniques, and deploy it to an Android demo app that can run any compatible TFLite LLMs.
|
|
|
|
|
|
|
Bring ML ideas to life using Visual Blocks
|
Visual Blocks is a new graphical programming framework for rapid prototyping and experimentation. Use powerful machine learning building blocks like PaLM 2, iterate within a visual interface, and easily deploy.
|
|
|
|
|
|
|
Expanding access to ultrasound technology with TensorFlow Lite
|
Read how Google’s Health AI team is working to expand global access to maternal healthcare by building a mobile-optimized fetal ultrasound system using
TensorFlow Lite
for on-device inference.
|
|
|
|
|
|
|
Visualize and interpret decision trees with dtreeviz
|
Use the dtreeviz library with
TensorFlow Decision Forests
to visualize how each decision node in a tree splits up a specific feature’s domain and show the distribution of training instances in each prediction.
|
|
|
|
|
|
|
|
Augment recommendation systems with state-of-the-art LLMs
|
Explore how you can use the
PaLM API
to create recommendations in chat applications, generate and sort recommendations, use embeddings to retrieve unknown candidates, and more.
|
|
|
|
|
|
|
Transitioning from software engineering to ML engineering
|
What are the key mindset differences between Machine Learning Engineering (MLE) and Software Engineering (SWE)? Find out what a typical workday looks like for each role, their complexities, and how they differ from planning to defining success.
|
|
|
|
|
|
|
|
|
|
|
Stay Connected
|
|
|
|
|
|
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],[],[],[]]