The difficulty of deploying various deep learning (DL) models on diverse DL hardware has
boosted the research and development of DL compilers in the community. Several DL …

Collaborative machine learning and related techniques such as federated learning allow
multiple participants, each with his own training dataset, to build a joint model by training …

Embeddings are functions that map raw input data to low-dimensional vector
representations, while preserving important semantic information about the inputs. Pre …

Motion sensors such as accelerometers and gyroscopes measure the instant acceleration
and rotation of a device, in three dimensions. Raw data streams from motion sensors …

Internet-of-Things (IoT) devices and applications are being deployed in our homes and
workplaces. These devices often rely on continuous data collection to feed machine learning …

The ever-growing advances of deep learning in many areas including vision,
recommendation systems, natural language processing, etc., have led to the adoption of …

" Overlearning" means that a model trained for a seemingly simple objective implicitly learns
to recognize attributes and concepts that are (1) not part of the learning objective, and (2) …

This article presents an analysis of data extraction for classification using correlation
coefficient and fuzzy model. Several traditional methods of data extraction are used for …

Federated learning still faces many problems from research to technology implementation
and the most critical problem is that the communication efficiency is not high. Therefore, the …

Collaborative inference (co-inference) accelerates deep neural network inference via
extracting representations at the device and making predictions at the edge server, which …