An official website of the United States government
The past decade has witnessed the great success of deep neural networks in various domains. However, deep neural networks are very resource-intensive in terms of energy consumption, data requirements, and high computational costs. With the recent increasing need for the autonomy of machines in the real world, e.g., self-driving vehicles, drones, and collaborative robots, exploitation of deep neural networks in those applications has been actively investigated. In those applications, energy and computational efficiencies are especially important because of the need for real-time responses and the limited energy supply. A promising solution to these previously infeasible applications has recently been given by biologically plausible spiking neural networks. Spiking neural networks aim to bridge the gap between neuroscience and machine learning, using biologically realistic models of neurons to carry out the computation. Due to their functional similarity to the biological neural network, spiking neural networks can embrace the sparsity found in biology and are highly compatible with temporal code. Our contributions in this work are: (i) we give a comprehensive review of theories of biological neurons; (ii) we present various existing spike-based neuron models, which have been studied in neuroscience; (iii) we detail synapse models; (iv) we provide a review of artificial neural networks; (v) we provide detailed guidance on how to train spike-based neuron models; (vi) we revise available spike-based neuron frameworks that have been developed to support implementing spiking neural networks; (vii) finally, we cover existing spiking neural network applications in computer vision and robotics domains. The paper concludes with discussions of future perspectives.
more »
« less
Taking Transactivity Detection to a New Level
Transactivity is a valued collaborative process, which has been associated with elevated learning gains, collaborative product quality, and knowledge transfer within teams. Dynamic forms of collaboration support have made use of real time monitoring of transactivity, and automation of its analysis has been affirmed as valuable to the field. Early models were able to achieve high reliability within restricted domains. More recent approaches have achieved a level of generality across learning domains. In this study, we investigate generalizability of models developed primarily in computer science courses to a new student population, namely, masters students in a leadership course, where we observe strikingly different patterns of transactive exchange than in prior studies. This difference prompted both a reformulation of the coding standards and innovation in the modeling approach, both of which we report on here.
more »
« less
- Award ID(s):
- 1822831
- PAR ID:
- 10295170
- Date Published:
- Journal Name:
- Proceedings of the first annual meeting of the International Society of the Learning Sciences
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME [39], are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the method itself and harming user trust. In this paper, we propose S-LIME, which utilizes a hypothesis testing framework based on central limit theorem for determining the number of perturbation points needed to guarantee stability of the resulting explanation. Experiments on both simulated and real world data sets are provided to demonstrate the effectiveness of our method.more » « less
-
For nearly two decades, conversational agents have been used to structure group interactions in online chat-based environments. More recently, this form of dynamic support for collaborative learning has been extended to physical spaces using a combination of multimodal sensing technologies and instrumentation installed within a physical space. This demo extends the reach of dynamic support for collaboration still further through an application of what has recently been termed on-device machine learning, which enables a portable form of multimodal detection to trigger real-time responses.more » « less
-
null (Ed.)The prevalence of deep learning has drawn attention to the privacy protection of sensitive data. Various privacy threats have been presented, where an adversary can steal model owners' private data. Meanwhile, countermeasures have also been introduced to achieve privacy-preserving deep learning. However, most studies only focused on data privacy during training, and ignored privacy during inference. In this paper, we devise a new set of attacks to compromise the inference data privacy in collaborative deep learning systems. Specifically, when a deep neural network and the corresponding inference task are split and distributed to different participants, one malicious participant can accurately recover an arbitrary input fed into this system, even if he has no access to other participants' data or computations, or to prediction APIs to query this system. We evaluate our attacks under different settings, models and datasets, to show their effectiveness and generalization. We also study the characteristics of deep learning models that make them susceptible to such inference privacy threats. This provides insights and guidelines to develop more privacy-preserving collaborative systems and algorithms.more » « less
-
Communities of practice (CoPs) play a crucial role in cross-pollination and learning within various skill-based and craft domains. These communities often share common materials, concepts, and techniques across related practices. However, due to their insular nature, exchanging knowledge between CoPs has been challenging, leading to fragmented knowledge marked by differing vocabularies and contexts. To address this issue, we introduce Anther, a system designed to highlight shared concepts and semantic overlap between distinct CoPs. Anther projects concepts onto a 2-dimensional space, providing users with comprehensive, contextual, and conceptual views. We conducted a user study, demonstrating Anther’s effectiveness in aggregating and disseminating community-based knowledge, bridging gaps between CoPs, and supporting the cross-pollination of knowledge between CoPs. Further, we present interaction vignettes that illustrate how Anther can ease entry into new domains and aide in discovering new creative techniques. This work can benefit maker communities by fostering collaborative knowledge-building across diverse domains.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
