Starting with Machine Learning on devices like MCU - Part 9 (What is TensorFlow?)

TensorFlow is an open-source machine learning and deep learning framework developed by Google. It helps developers and researchers build, train, and deploy AI models easily. For Microcontrollers, TensorFlow Lite will be used. 

Purpose of TensorFlow: It is used to create neural networks for tasks like image recognition, natural language processing, time series forecasting, etc.

Core idea: TensorFlow represents data as tensors (multi-dimensional arrays) and operations as a computational graph, that’s where the name “TensorFlow” comes from (tensors flowing through a graph).

Languages: Primarily used with Python also supports C++ also.

Key features of TensorFlow:

• Supports both CPU and GPU acceleration.
• Works well for both training and inference.
• Has high-level APIs like Keras for building models easily.
• Scales from small experiments to large distributed systems.