教学课程资源库 更多>>

关键词： Computer science   Human behaviour  

摘要： The power of human language and thought arises from systematic compositionality-the algebraic ability to understand and produce novel combinations from known components. Fodor and Pylyshyn(1) famously argued that artificial neural networks lack this capacity and are therefore not viable models of the mind. Neural networks have advanced considerably in the years since, yet the systematicity challenge persists. Here we successfully address Fodor and Pylyshyn's challenge by providing evidence that neural networks can achieve human-like systematicity when optimized for their compositional skills. To do so, we introduce the meta-learning for compositionality (MLC) approach for guiding training through a dynamic stream of compositional tasks. To compare humans and machines, we conducted human behavioural experiments using an instruction learning paradigm. After considering seven different models, we found that, in contrast to perfectly systematic but rigid probabilistic symbolic models, and perfectly flexible but unsystematic neural networks, only MLC achieves both the systematicity and flexibility needed for human-like generalization. MLC also advances the compositional skills of machine learning systems in several systematic generalization benchmarks. Our results show how a standard neural network architecture, optimized for its compositional skills, can mimic human systematic generalization in a head-to-head comparison.

关键词： Computer science   Electrical and electronic engineering   Optoelectronic devices and components  

摘要： Photonic computing enables faster and more energy-efficient processing of vision data(1-5). However, experimental superiority of deployable systems remains a challenge because of complicated optical nonlinearities, considerable power consumption of analog-to-digital converters (ADCs) for downstream digital processing and vulnerability to noises and system errors(1,6-8). Here we propose an all-analog chip combining electronic and light computing (ACCEL). It has a systemic energy efficiency of 74.8 peta-operations per second per watt and a computing speed of 4.6 peta-operations per second (more than 99% implemented by optics), corresponding to more than three and one order of magnitude higher than state-of-the-art computing processors, respectively. After applying diffractive optical computing as an optical encoder for feature extraction, the light-induced photocurrents are directly used for further calculation in an integrated analog computing chip without the requirement of analog-to-digital converters, leading to a low computing latency of 72 ns for each frame. With joint optimizations of optoelectronic computing and adaptive training, ACCEL achieves competitive classification accuracies of 85.5%, 82.0% and 92.6%, respectively, for Fashion-MNIST, 3-class ImageNet classification and time-lapse video recognition task experimentally, while showing superior system robustness in low-light conditions (0.14 fJ mu m(-2) each frame). ACCEL can be used across a broad range of applications such as wearable devices, autonomous driving and industrial inspections.

关键词： Computer science   Technology   Policy  

摘要： Artificial-intelligence tools are transforming data-driven science - better ethical standards and more robust data curation are needed to fuel the boom and prevent a bust. Artificial-intelligence tools are transforming data-driven science - better ethical standards and more robust data curation are needed to fuel the boom and prevent a bust.

关键词： Computer science   Ethics   Machine learning   Society  

摘要： Robust regulation of AI technologies will be crucial to protecting against harms. Researchers’ voices must be heard. [Figure not available: see fulltext.] © 2023, Springer Nature Limited.

关键词： Computer science identities   relational space   celebrated identities   sense of belonging   narrative interviews  

摘要： There is a call for more students to continue into computer science (CS), but as many leave their studies before completing, there is a potential in retaining students rather than focusing on recruitment alone. The retention literature proposes 'sense of belonging' as a key concept. This paper contributes with nuancing how sense of belonging is shaped differently within different spaces at the same CS study-programme, by drawing on narrative interviews and ethnographic fieldwork with BA-students, analysed through a spatial analytic lens. By applying the metaphors of a solar system and force fields, we investigate how sense of belonging was constructed within relational spaces and students' identity-negotiations within them. Three spaces are found: The studylounge (the epicenter of the solar system), the pulsating planet, and the distant isolated planet. Conclusions show how the epicenter are enforced by teaching and learning activities, and how broadening what counts hold potential to retain students.

关键词： Studios  

摘要： This study examines the adaptation of the problem-solving studio to computer science education by combining it with pair programming. Pair programming is a software engineering practice in industry, but has seen mixed results in the classroom. Recent research suggests that pair programming has promise and potential to be an effective pedagogical tool, however what constitutes good instructional design and implementation for pair programming in the classroom is not clear. We developed a framework for instructional design for pair programming by adapting the problem-solving studio (PSS), a pedagogy originally from biomedical engineering. PSS involves teams of students solving open-ended problems with real-time feedback given by the instructor Notably, PSS uses problems of adjustable difficulty to keep students of all levels engaged and functioning within the zone of proximal development. The course structure has three stages, first starting with demonstration, followed by a PSS session, then finishing with a debrief. We studied the combination of PSS and pair programming in a CS1 class over three years. Surveys of the students report a high level of engagement, learning, and motivation. © 2023, CC BY.

关键词： Computer science  

摘要： Multitasking electrodes could enable 1,000 qubits to fit onto one device.

关键词： Computer science   Mathematics and computing   Brain  

摘要： IBM's NorthPole processor sidesteps need to access external memory, boosting computing power and saving energy.

关键词： Computer science   Technology   Neuroscience  

摘要： A neural-network-based artificial intelligence outperforms ChatGPT at quickly folding new words into its lexicon, a key aspect of human intelligence. A neural-network-based artificial intelligence outperforms ChatGPT at quickly folding new words into its lexicon, a key aspect of human intelligence.