10 More lessons learned from building real-life Machine Learning systems — Part I
Xavier Amatriain
2185

Good points. Really agree with your insights about the use of unlabelled data for Unsupervised Learning as well as unsupervised pre-training Deep Networks (denoising autoencoders & RBMs) — takes a while to master these techniques and incorporate them into one’s ML pipelines— am slowly getting comfortable with these. Looking forward to the next 5 & beyond.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.