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.
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
- NSF-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
-
more » « less
-
null (Ed.)Today’s classrooms are remarkably different from those of yesteryear. In place of individual students responding to the teacher from neat rows of desks, one more typically finds students working in groups on projects, with a teacher circulating among groups. AI applications in learning have been slow to catch up, with most available technologies focusing on personalizing or adapting instruction to learners as isolated individuals. Meanwhile, an established science of Computer Supported Collaborative Learning has come to prominence, with clear implications for how collaborative learning could best be supported. In this contribution, I will consider how intelligence augmentation could evolve to support collaborative learning as well as three signature challenges of this work that could drive AI forward. In conceptualizing collaborative learning, Kirschner and Erkens (2013) provide a useful 3x3 framework in which there are three aspects of learning (cognitive, social and motivational), three levels (community, group/team, and individual) and three kinds of pedagogical supports (discourse-oriented, representation-oriented, and process-oriented). As they engage in this multiply complex space, teachers and learners are both learning to collaborate and collaborating to learn. Further, questions of equity arise as we consider who is able to participate and in which ways. Overall, this analysis helps us see the complexity of today’s classrooms and within this complexity, the opportunities for augmentation or “assistance to become important and even essential. An overarching design concept has emerged in the past 5 years in response to this complexity, the idea of intelligent augmentation for “orchestrating” classrooms (Dillenbourg, et al, 2013). As a metaphor, orchestration can suggest the need for a coordinated performance among many agents who are each playing different roles or voicing different ideas. Practically speaking, orchestration suggests that “intelligence augmentation” could help many smaller things go well, and in doing so, could enable the overall intention of the learning experience to succeed. Those smaller things could include helping the teacher stay aware of students or groups who need attention, supporting formation of groups or transitions from one activity to the next, facilitating productive social interactions in groups, suggesting learning resources that would support teamwork, and more. A recent panel of AI experts identified orchestration as an overarching concept that is an important focus for near-term research and development for intelligence augmentation (Roschelle, Lester & Fusco, 2020). Tackling this challenging area of collaborative learning could also be beneficial for advancing AI technologies overall. Building AI agents that better understand the social context of human activities has broad importance, as does designing AI agents that can appropriately interact within teamwork. Collaborative learning has trajectory over time, and designing AI systems that support teams not just with a short term recommendation or suggestion but in long-term developmental processes is important. Further, classrooms that are engaged in collaborative learning could become very interesting hybrid environments, with multiple human and AI agents present at once and addressing dual outcome goals of learning to collaborate and collaborating to learn; addressing a hybrid environment like this could lead to developing AI systems that more robustly help many types of realistic human activity. In conclusion, the opportunity to make a societal impact by attending to collaborative learning, the availability of growing science of computer-supported collaborative learning and the need to push new boundaries in AI together suggest collaborative learning as a challenge worth tackling in coming years.more » « less
-
null (Ed.)Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have shown external attacks such as adversarial examples that tamper the integrity of DNNs using maliciously crafted inputs. However, the security implication of internal threats (i.e., hardware vulnerabilities) to DNN models has not yet been well understood. In this paper, we demonstrate the first hardware-based attack on quantized deep neural networks–DeepHammer–that deterministically induces bit flips in model weights to compromise DNN inference by exploiting the rowhammer vulnerability. DeepHammer performs an aggressive bit search in the DNN model to identify the most vulnerable weight bits that are flippable under system constraints. To trigger deterministic bit flips across multiple pages within a reasonable amount of time, we develop novel system-level techniques that enable fast deployment of victim pages, memory-efficient rowhammering and precise flipping of targeted bits. DeepHammer can deliberately degrade the inference accuracy of the victim DNN system to a level that is only as good as random guess, thus completely depleting the intelligence of targeted DNN systems. We systematically demonstrate our attacks on real systems against 11 DNN architectures with 4 datasets corresponding to different application domains. Our evaluation shows that DeepHammer is able to successfully tamper DNN inference behavior at run-time within a few minutes. We further discuss several mitigation techniques from both algorithm and system levels to protect DNNs against such attacks. Our work highlights the need to incorporate security mechanisms in future deep learning systems to enhance the robustness against hardware-based deterministic fault injections.more » « less
-
There have been numerous demands for enhancements in the way undergraduate learning occurs today, especially at a time when the value of higher education continues to be called into question (The Boyer 2030 Commission, 2022). One type of demand has been for the increased integration of subjects/disciplines around relevant issues/topics—with a more recent trend of seeking transdisciplinary learning experiences for students (Sheets, 2016; American Association for the Advancement of Science, 2019). Transdisciplinary learning can be viewed as the holistic way of working equally across disciplines to transcend their own disciplinary boundaries to form new conceptual understandings as well as develop new ways in which to address complex topics or challenges (Ertas, Maxwell, Rainey, & Tanik, 2003; Park & Son, 2010). This transdisciplinary approach can be important as humanity’s problems are not typically discipline specific and require the convergence of competencies to lead to innovative thinking across fields of study. However, higher education continues to be siloed which makes the authentic teaching of converging topics, such as innovation, human-technology interactions, climate concerns, or harnessing the data revolution, organizationally difficult (Birx, 2019; Serdyukov, 2017). For example, working across a university’s academic units to collaboratively teach, or co-teach, around topics of convergence are likely to be rejected by the university systems that have been built upon longstanding traditions. While disciplinary expertise is necessary and one of higher education’s strengths, the structures and academic rigidity that come along with the disciplinary silos can prevent modifications/improvements to the roles of academic units/disciplines that could better prepare students for the future of both work and learning. The balancing of disciplinary structure with transdisciplinary approaches to solving problems and learning is a challenge that must be persistently addressed. These institutional challenges will only continue to limit universities seeking toward scaling transdisciplinary programs and experimenting with novel ways to enhance the value of higher education for students and society. This then restricts innovations to teaching and also hinders the sharing of important practices across disciplines. To address these concerns, a National Science Foundation Improving Undergraduate STEM Education project team, which is the topic of this paper, has set the goal of developing/implementing/testing an authentically transdisciplinary, and scalable educational model in an effort to help guide the transformation of traditional undergraduate learning to span academics silos. This educational model, referred to as the Mission, Meaning, Making (M3) program, is specifically focused on teaching the crosscutting practices of innovation by a) implementing co-teaching and co-learning from faculty and students across different academic units/colleges as well as b) offering learning experiences spanning multiple semesters that immerse students in a community that can nourish both their learning and innovative ideas. As a collaborative initiative, the M3 program is designed to synergize key strengths of an institution’s engineering/technology, liberal arts, and business colleges/units to create a transformative undergraduate experience focused on the pursuit of innovation—one that reaches the broader campus community, regardless of students’ backgrounds or majors. Throughout the development of this model, research was conducted to help identify institutional barriers toward creating such a cross-college program at a research-intensive public university along with uncovering ways in which to address these barriers. While data can show how students value and enjoy transdisciplinary experiences, universities are not likely to be structured in a way to support these educational initiatives and they will face challenges throughout their lifespan. These challenges can result from administration turnover whereas mutual agreements across colleges may then vanish, continued disputes over academic territory, and challenges over resource allotments. Essentially, there may be little to no incentives for academic departments to engage in transdisciplinary programming within the existing structures of higher education. However, some insights and practices have emerged from this research project that can be useful in moving toward transdisciplinary learning around topics of convergence. Accordingly, the paper will highlight features of an educational model that spans disciplines along with the workarounds to current institutional barriers. This paper will also provide lessons learned related to 1) the potential pitfalls with educational programming becoming “un-disciplinary” rather than transdisciplinary, 2) ways in which to incentivize departments/faculty to engage in transdisciplinary efforts, and 3) new structures within higher education that can be used to help faculty/students/staff to more easily converge to increase access to learning across academic boundaries.more » « less
-
Applying machine learning (ML) in design flow is a popular trend in Electronic Design Automation (EDA) with various applications from design quality predictions to optimizations. Despite its promise, which has been demonstrated in both academic researches and industrial tools, its effectiveness largely hinges on the availability of a large amount of high-quality training data. In reality, EDA developers have very limited access to the latest design data, which is owned by design companies and mostly confidential. Although one can commission ML model training to a design company, the data of a single company might be still inadequate or biased, especially for small companies. Such data availability problem is becoming the limiting constraint on future growth of ML for chip design. In this work, we propose an Federated-Learning based approach for well-studied ML applications in EDA. Our approach allows an ML model to be collaboratively trained with data from multiple clients but without explicit access to the data for respecting their data privacy. To further strengthen the results, we co-design a customized ML model FLNet and its personalization under the decentralized training scenario. Experiments on a comprehensive dataset show that collaborative training improves accuracy by 11% compared with individual local models, and our customized model FLNet significantly outperforms the best of previous routability estimators in this collaborative training flow.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
