Hardware approximate techniques for deep neural network accelerators: A survey
… [45], the billions of mobile devices running DNN inference, and the rapid growth of AI chips,…
used in DNN inference. Rather than executing all the required mathematical operations with …
used in DNN inference. Rather than executing all the required mathematical operations with …
Bayesian-assisted inference from visualized data
YS Kim, P Kayongo… - … on Visualization and …, 2020 - ieeexplore.ieee.org
… further mathematical details below. Finally, note that Bayesian inference in cognition is …
to believe that elicited priors are not a perfect representation of a user’s prior beliefs, we find …
to believe that elicited priors are not a perfect representation of a user’s prior beliefs, we find …
[HTML][HTML] Neural dynamics under active inference: Plausibility and efficiency of information processing
… under active inference are metabolically efficient and suggest that neural representations
in … brain, but also yield useful insights into mathematical optimisation and machine learning. …
in … brain, but also yield useful insights into mathematical optimisation and machine learning. …
[HTML][HTML] Is the free-energy principle a formal theory of semantics? From variational density dynamics to neural and phenotypic representations
… representations are mathematical, rather than cognitive, and a fictionalist or instrumentalist
account, according to which representations … -energy principle and active inference, we argue …
account, according to which representations … -energy principle and active inference, we argue …
[HTML][HTML] Embodied Learning in Early Mathematics Education: Translating Research into Principles to Inform Teaching
… infer the development of particular internal representation … the origins of embodied
representation lie in the movement of … cognition theory and representation theory in mathematics …
representation lie in the movement of … cognition theory and representation theory in mathematics …
Planning nets: A representation for formalizing analogies and semantic models of procedural skills
K VanLehn, JS Brown - Aptitude, learning, and instruction, 2021 - taylorfrancis.com
… from the computational procedures of arithmetic, even though … We limited our examples to
arithmetic for several reasons. … planning inferences do deal with the object representation. …
arithmetic for several reasons. … planning inferences do deal with the object representation. …
Relations between component reading skills, inferences, and comprehension performance in community college readers
… local discourse level processes (ie, constructing accurate representations of sentences, and
… were significant predictors of elaborative inferences and performance on the traditional and …
… were significant predictors of elaborative inferences and performance on the traditional and …
Vega: A ten-core SoC for IoT endnodes with DNN acceleration and cognitive wake-up from MRAM-based state-retentive sleep mode
… performance and efficiency, mainly focusing on inference [4], [5], training [6] of DNNs, and
exploiting low- and tunable-precision arithmetic to … -dimensional holistic representations of the …
exploiting low- and tunable-precision arithmetic to … -dimensional holistic representations of the …
Revisiting hyperdimensional learning for fpga and low-power architectures
… HDC during the inference, ie, 83% average performance for all … In this paper, we exploit the
mathematical orthogonality of … store P hypervectors as binary representation and use them as …
mathematical orthogonality of … store P hypervectors as binary representation and use them as …
Classification using hyperdimensional computing: A review
… and requires less time for training and inference [9]. These features are a result of its ultra-wide
data representation and underlying mathematical operations. One thing that should be …
data representation and underlying mathematical operations. One thing that should be …