Search Results for author:
Found 19 papers, 4 papers with code
A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it
In recent times, advances in artificial intelligence (AI) and IoT have enabled seamless and viable maintenance of appliances in home and building environments.
Universum GANs: Improving GANs through contradictions
Limited availability of labeled-data makes any supervised learning problem challenging.
Stochastic Whitening Batch Normalization
BN uses scaling and shifting to normalize activations of mini-batches to accelerate convergence and improve generalization.
Stabilizing Bi-Level Hyperparameter Optimization using Moreau-Yosida Regularization
This research proposes to use the Moreau-Yosida envelope to stabilize the convergence behavior of bi-level Hyperparameter optimization solvers, and introduces the new algorithm called Moreau-Yosida regularized Hyperparameter Optimization (MY-HPO) algorithm.
Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
With the general trend of increasing Convolutional Neural Network (CNN) model sizes, model compression and acceleration techniques have become critical for the deployment of these models on edge devices.
Multiclass Learning from Contradictions
We introduce the notion of learning from contradictions, a. k. a Universum learning, for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM).
Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning
Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming.
On-Device Machine Learning: An Algorithms and Learning Theory Perspective
However, on-device learning is an expansive field with connections to a large number of related topics in AI and machine learning (including online learning, model adaptation, one/few-shot learning, etc.).
Variable Metric Proximal Gradient Method with Diagonal Barzilai-Borwein Stepsize
Under this metric selection for VM-PG, the theoretical convergence is analyzed.
Improving Model Training by Periodic Sampling over Weight Distributions
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentum, Adam) for a variety of vision problems (classification, detection, segmentation).
Is it Safe to Drive? An Overview of Factors, Challenges, and Datasets for Driveability Assessment in Autonomous Driving
Furthermore, by discussions of what driving scenarios are not covered by existing public datasets and what driveability factors need more investigation and data acquisition, this paper aims to encourage both targeted dataset collection and the proposal of novel driveability metrics that enhance the robustness of autonomous cars in adverse environments.
Multiclass Universum SVM
We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM).
Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling
We perform a variety of analysis using the MNIST dataset and validate the approach with a number of DNN models using pre-trained models on the ImageNet dataset.
Effective Building Block Design for Deep Convolutional Neural Networks using Search
We apply this technique to generate models for multiple image datasets and show that these models achieve performance comparable to state-of-the-art (and even surpassing the state-of-the-art in one case).
Concept Drift Detection and Adaptation with Hierarchical Hypothesis Testing
A fundamental issue for statistical classification models in a streaming environment is that the joint distribution between predictor and response variables changes over time (a phenomenon also known as concept drifts), such that their classification performance deteriorates dramatically.
Deep Symbolic Representation Learning for Heterogeneous Time-series Classification
In this paper, we consider the problem of event classification with multi-variate time series data consisting of heterogeneous (continuous and categorical) variables.
Universum Learning for Multiclass SVM
We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM).
Comparative Study of Deep Learning Software Frameworks
The study is performed on several types of deep learning architectures and we evaluate the performance of the above frameworks when employed on a single machine for both (multi-threaded) CPU and GPU (Nvidia Titan X) settings.
Risk Bounds for Randomized Sample Compressed Classifiers
By extending the recently proposed Occamâs Hammer principle to the data-dependent settings, we derive point-wise versions of the bounds on the stochastic sample compressed classifiers and also recover the corresponding classical PAC-Bayes bound.
