Digests » 132
this week's favorite
The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution.
In videos past of this deep learning series, we have going from learning about the origins of the field of deep learning to how the structure of the neural network was conceived, along with working through an intuitive example covering the fundamentals of deep learning.
These practice exercises cover the productionization aspects of the machine learning life cycle, also referred to as MLOps. Topics covered include training and inference reproducibility via Docker, web application fundamentals, the differences between SQL/NoSQL databases, and how to organize and validate your data quality.
BERT powers almost every single English based query done on Google Search, the company said during its virtual Search on 2020 event Thursday. That’s up from just 10% of English queries when Google first announced the use of the BERT algorithm in Search last October.
With the advent of deep learning, implementing an object detection system has become fairly trivial. There are a great many frameworks facilitating the process, and as I showed in a previous post, it’s quite easy to create a fast object detection model with YOLOv5.