To this end, we analyse over 16k of the most popular apps in the Google Play Store to characterise their DNN usage and performance across devices of different capabilities, both across tiers and generations.
Collectively, these results highlight the critical need for further exploration as to how the various cross-stack solutions can be best combined in order to bring the latest advances in deep learning close to users, in a robust and efficient manner.
Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs).
FjORD alleviates the problem of client system heterogeneity by tailoring the model width to the client's capabilities.
On-device machine learning is becoming a reality thanks to the availability of powerful hardware and model compression techniques.
Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices.
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs).
We also explore specific manifestations of abusive behavior, i. e., cyberbullying and cyberaggression, in one of the hate-related communities (Gamergate).
In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring.
Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data.
Remembering our day-to-day social interactions is challenging even if you aren't a blue memory challenged fish.
Hate speech, offensive language, sexism, racism and other types of abusive behavior have become a common phenomenon in many online social media platforms.
5 code implementations • 1 Feb 2018 • Antigoni-Maria Founta, Constantinos Djouvas, Despoina Chatzakou, Ilias Leontiadis, Jeremy Blackburn, Gianluca Stringhini, Athena Vakali, Michael Sirivianos, Nicolas Kourtellis
In recent years, offensive, abusive and hateful language, sexism, racism and other types of aggressive and cyberbullying behavior have been manifesting with increased frequency, and in many online social media platforms.
Social and Information Networks 68T06 K.4.2
Besides using classical gradient-boosted trees, we demonstrate how to make continual predictions using a recurrent neural network (RNN).
Common approaches to text categorization essentially rely either on n-gram counts or on word embeddings.
We present a practical approach for processing mobile sensor time series data for continual deep learning predictions.
Our results indicate that, compared to the best baseline, tree-based models can deliver up to 14% better forecasts for regular hot spots and 153% better forecasts for non-regular hot spots.
The layouts of the buildings we live in shape our everyday lives.
Computers and Society Human-Computer Interaction Social and Information Networks