The Experts below are selected from a list of 315 Experts worldwide ranked by ideXlab platform
Ferenc Jordan - One of the best experts on this subject based on the ideXlab platform.
-
social Network analysis of animal behaviour a promising tool for the study of sociality
Animal Behaviour, 2008Co-Authors: Tina W Wey, Daniel T Blumstein, Weiwei Shen, Ferenc JordanAbstract:Social animals live and interact together, forming complex relationships and social structure. These relationships can have important fitness consequences, but most studies do not explicitly measure those relationships. An approach that explicitly measures relationships will further our understanding of social complexity and the consequences of both direct and indirect interactions. Social Network analysis is the study of social groups as Networks of nodes connected by social ties. This approach examines individuals and groups in the context of relationships between group members. Application of social Network analysis to animal behaviour can advance the field by identifying and quantifying specific attributes of social relationships, many of which are not captured by more common measures of sociality, such as group size. Sophisticated methods for Network construction and analysis exist in other fields, but until recently, have seen relatively little application to animal systems. We present a brief history of social Network analysis, a description of basic concepts and previous applications to animal behaviour. We then highlight relevance and constraints of some Network measures, including results from an original study of the effect of sampling on Network Parameter estimates, and we end with promising directions for research. By doing so, we provide a prospective overview of social Network analysis' general utility for the study of animal social behaviour.
Massimiliano Mancini - One of the best experts on this subject based on the ideXlab platform.
-
adding new tasks to a single Network with weight transformations using binary masks
European Conference on Computer Vision, 2018Co-Authors: Massimiliano Mancini, Elisa Ricci, Barbara Caputo, Samuel Rota BuloAbstract:Visual recognition algorithms are required today to exhibit adaptive abilities. Given a deep model trained on a specific, given task, it would be highly desirable to be able to adapt incrementally to new tasks, preserving scalability as the number of new tasks increases, while at the same time avoiding catastrophic forgetting issues. Recent work has shown that masking the internal weights of a given original conv-net through learned binary variables is a promising strategy. We build upon this intuition and take into account more elaborated affine transformations of the convolutional weights that include learned binary masks. We show that with our generalization it is possible to achieve significantly higher levels of adaptation to new tasks, enabling the approach to compete with fine tuning strategies by requiring slightly more than 1 bit per Network Parameter per additional task. Experiments on two popular benchmarks showcase the power of our approach, that achieves the new state of the art on the Visual Decathlon Challenge.
Tina W Wey - One of the best experts on this subject based on the ideXlab platform.
-
social Network analysis of animal behaviour a promising tool for the study of sociality
Animal Behaviour, 2008Co-Authors: Tina W Wey, Daniel T Blumstein, Weiwei Shen, Ferenc JordanAbstract:Social animals live and interact together, forming complex relationships and social structure. These relationships can have important fitness consequences, but most studies do not explicitly measure those relationships. An approach that explicitly measures relationships will further our understanding of social complexity and the consequences of both direct and indirect interactions. Social Network analysis is the study of social groups as Networks of nodes connected by social ties. This approach examines individuals and groups in the context of relationships between group members. Application of social Network analysis to animal behaviour can advance the field by identifying and quantifying specific attributes of social relationships, many of which are not captured by more common measures of sociality, such as group size. Sophisticated methods for Network construction and analysis exist in other fields, but until recently, have seen relatively little application to animal systems. We present a brief history of social Network analysis, a description of basic concepts and previous applications to animal behaviour. We then highlight relevance and constraints of some Network measures, including results from an original study of the effect of sampling on Network Parameter estimates, and we end with promising directions for research. By doing so, we provide a prospective overview of social Network analysis' general utility for the study of animal social behaviour.
Misra S - One of the best experts on this subject based on the ideXlab platform.
-
Reconfigure and Reuse: Interoperable Wearables for Healthcare IoT
2020Co-Authors: Pathak N, Mukherjee A, Misra SAbstract:In this work, we propose Over-The-Air (OTA)-based reconfigurable IoT health-monitoring wearables, which tether wirelessly to a low-power and portable central processing and communication hub (CPH). This hub is responsible for the proper packetization and transmission of the physiological data received from the individual sensors connected to each wearable to a remote server. Each wearable consists of a sensor, a communication adapter, and its power module. We introduce low-power adapters with each sensor, which facilitates the sensor-CPH linkups and on-demand Network Parameter reconfigurations. The newly introduced adapter supports the interoperability of heterogeneous sensors by eradicating the need for sensor-specific modules through OTA-based reconfiguration. The reconfiguration feature allows for new sensors to connect to an existing adapter, without changing the hardware units or any external interface. The proposed system is scalable and enables multiple sensors to connect in a Network and work in synchronization with the CPH to achieve semantic and device interoperability among the sensors. We test the implementation in real-time using three different health-monitoring sensor types - temperature, pulse oximeter, and ECG. The results of our real-time system evaluation depict that the proposed system is reliable and responsive in terms of the achieved packet delivery ratio, received signal strength, and energy consumption
-
Reconfigure and Reuse: Interoperable Wearables for Healthcare IoT
2020Co-Authors: Pathak N, Mukherjee A, Misra SAbstract:© 2020 IEEE. In this work, we propose Over-The-Air (OTA)-based reconfigurable IoT health-monitoring wearables, which tether wirelessly to a low-power and portable central processing and communication hub (CPH). This hub is responsible for the proper packetization and transmission of the physiological data received from the individual sensors connected to each wearable to a remote server. Each wearable consists of a sensor, a communication adapter, and its power module. We introduce low-power adapters with each sensor, which facilitates the sensor-CPH linkups and on-demand Network Parameter reconfigurations. The newly introduced adapter supports the interoperability of heterogeneous sensors by eradicating the need for sensor-specific modules through OTA-based reconfiguration. The reconfiguration feature allows for new sensors to connect to an existing adapter, without changing the hardware units or any external interface. The proposed system is scalable and enables multiple sensors to connect in a Network and work in synchronization with the CPH to achieve semantic and device interoperability among the sensors. We test the implementation in real-time using three different health-monitoring sensor types - temperature, pulse oximeter, and ECG. The results of our real-time system evaluation depict that the proposed system is reliable and responsive in terms of the achieved packet delivery ratio, received signal strength, and energy consumption
Svetlana Lazebnik - One of the best experts on this subject based on the ideXlab platform.
-
piggyback adapting a single Network to multiple tasks by learning to mask weights
European Conference on Computer Vision, 2018Co-Authors: Arun Mallya, Dillon Davis, Svetlana LazebnikAbstract:This work presents a method for adapting a single, fixed deep neural Network to multiple tasks without affecting performance on already learned tasks. By building upon ideas from Network quantization and pruning, we learn binary masks that “piggyback” on an existing Network, or are applied to unmodified weights of that Network to provide good performance on a new task. These masks are learned in an end-to-end differentiable fashion, and incur a low overhead of 1 bit per Network Parameter, per task. Even though the underlying Network is fixed, the ability to mask individual weights allows for the learning of a large number of filters. We show performance comparable to dedicated fine-tuned Networks for a variety of classification tasks, including those with large domain shifts from the initial task (ImageNet), and a variety of Network architectures. Our performance is agnostic to task ordering and we do not suffer from catastrophic forgetting or competition between tasks.
-
piggyback adapting a single Network to multiple tasks by learning to mask weights
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Arun Mallya, Dillon Davis, Svetlana LazebnikAbstract:This work presents a method for adapting a single, fixed deep neural Network to multiple tasks without affecting performance on already learned tasks. By building upon ideas from Network quantization and pruning, we learn binary masks that piggyback on an existing Network, or are applied to unmodified weights of that Network to provide good performance on a new task. These masks are learned in an end-to-end differentiable fashion, and incur a low overhead of 1 bit per Network Parameter, per task. Even though the underlying Network is fixed, the ability to mask individual weights allows for the learning of a large number of filters. We show performance comparable to dedicated fine-tuned Networks for a variety of classification tasks, including those with large domain shifts from the initial task (ImageNet), and a variety of Network architectures. Unlike prior work, we do not suffer from catastrophic forgetting or competition between tasks, and our performance is agnostic to task ordering. Code available at this https URL.