The models we trained in the past chapters offered us a glimpse of what we can do with TensorFlow.js. While insightful and useful, you could say that they were also uncomplicated. Those algorithms (linear regression, logistic regression, and k-means) were examples of traditional machine learning models. Typically, you would not use a tool like TF.js to implement them. Instead, most people would use a more specialized library like scikit-learn. Still, replicating them using a network-like structure is an excellent ...
© Juan De Dios Santos Rivera 2020
J. D. D. S. RiveraPractical TensorFlow.jshttps://doi.org/10.1007/978-1-4842-6273-3_44. Recognizing handwritten digits with convolutional neural networks
Juan De Dios Santos Rivera1
(1)
San Juan, PR, USA
Get Practical TensorFlow.js: Deep Learning in Web App Development now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
