Enhances mobile context prediction using weakly supervised learning.
problem Power consumption and limited training data for always-on context prediction.
method Weakly supervised learning framework for multi-modal sensing.
result Personalized context prediction model with improved accuracy.
NSMs use always-on stochasticity to normalize activations, improving convergence and performance.
problem Improving the robustness and generalizability of deep neural networks.
method Developed Neural Sampling Machines (NSMs) using always-on multiplicative stochasticity and simple threshold neurons.
result NSMs exhibit self-normalizing properties similar to Weight Normalization, speeding up convergence and preventing internal covariate shift.
An upper bound of the superbridge index of the connected sum of two knots is given in terms of the braid index of the summands. Using this upper bound and minimal polygonal presentations, we give an upper bound in terms of the superbridge index and the bridge index of the summands when they are torus knots. In contrast…
The problem of pursuing a moving target is always one of the main topics in navigation. In the literatures, there are two well-known algorithms called Pure Pursuit and Pure Rendezvous navigation in the 3-dimensional space R3. In this paper, these two methods are combined to introduce a novel family of pursu…
We propose an efficient end-to-end convolutional neural network architecture, AclNet, for audio classification. When trained with our data augmentation and regularization, we achieved state-of-the-art performance on the ESC-50 corpus with 85:65% accuracy. Our network allows configurations such that memory and compute r…
New KWS neural networks improve accuracy and power efficiency.
problem Maximizing accuracy and power efficiency in KWS systems.
method Hardware Aware Training (HAT) for LMU-based neural networks.
result Achieved state-of-the-art accuracy and low parameter counts.
New findings show the Gilmer-Masbaum map isn't always one-to-one.
problem Determining the injectivity of the Gilmer-Masbaum map on Kauffman bracket skein modules.
method Computed the image of the evaluation map for specific cases of mapping tori and analyzed homology classes.
result The restriction of the Gilmer-Masbaum map to certain homology classes is not injective.
New method reduces cloud usage for mobile/IoT predictions.
problem Minimizing cloud usage for mobile/IoT predictions while maintaining accuracy.
method Formulating the BL problem via bracketing functions h−,h+ from a simple class. result Improved performance over prior methods, validated on real-world datasets.
This paper introduces GLT for better input data representation in BNN and proposes a compact topology with block pruning.
problem Improving input data representation for Binary Neural Networks (BNN).
method Generic Learned Thermometer (GLT) for encoding, block pruning and Knowledge Distillation for compact topology.
result Significant accuracy gains and lightweight fully-binarized models with limited accuracy degradation.
New methods estimate survival functions with time-varying covariates.
problem Estimating survival functions with time-varying covariates.
method Generalized conditional inference and relative risk forests, adapted transformation forest.
result Proposed methods outperform traditional models in estimating survival functions.
Retraining stabilizes model influence on data.
problem Performativity in predictive models leads to feedback loops.
method Developed the stable signal principle to address retraining dynamics.
result Repeated risk minimization converges geometrically to stable signal direction.