<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>TensorFlow - Tag - Jorgen Bergstrom</title><link>https://bergstrom.org/tags/tensorflow/</link><description>TensorFlow - Tag - Jorgen Bergstrom</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><copyright>Jorgen Bergstrom</copyright><lastBuildDate>Tue, 28 May 2024 00:00:00 -0500</lastBuildDate><atom:link href="https://bergstrom.org/tags/tensorflow/" rel="self" type="application/rss+xml"/><item><title>Neural Network Analysis of Hammer Throw Distance using TensorFlow Keras</title><link>https://bergstrom.org/posts/nn_hammer_distance_tensorflow/</link><pubDate>Tue, 28 May 2024 00:00:00 -0500</pubDate><author>Jorgen Bergstrom</author><guid>https://bergstrom.org/posts/nn_hammer_distance_tensorflow/</guid><description>Summary The Keras Sequential model is a simple and straightforward way to build neural networks in Keras, a high-level neural networks API running on top of TensorFlow. The Sequential model allows you to stack layers sequentially, meaning each layer has exactly one input tensor and one output tensor. You start by creating an instance of the Sequential model, then add layers to it one by one. Each layer, such as Dense (fully connected), Convolutional, or LSTM (Long Shor-Term Memory), is added using the add method.</description></item></channel></rss>