Embedded machine learning is the process of running machine learning algorithms (including deep learning) on embedded systems, such as microcontrollers and single board computers. These videos come from the Coursera course: Introduction to Embedded Machine Learning. If you would like to take the full course, complete projects, and earn a certificate in embedded machine learning, please go here:

[ Ссылка ]

In this video, Alex introduces the concept of a mathematical "neuron" (inspired by brain neurons) and how it can be used to model data to make decisions and predictions. Layers of multiple neurons create a "neural network" and can be used for a variety of classification and prediction tasks.

Alex also introduces the concept of backpropagation, which can be used to automatically update the weights in a neural network so that the predicted output will more closely match the ground truth in the training data.

Once a model is trained, it can be used to make predictions on new data in a process known as "inference."

свернуть