Papers
Sun 14 Feb 2021
74 papers
- Self Regulated Learning Mechanism for Data Efficient Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Image Captioning using Multiple Transformers for Self-Attention Mechanism
- Finite Confluences and Closed Pattern Mining
- Multiple-shooting adjoint method for whole-brain dynamic causal modeling
- Communication-efficient Distributed Cooperative Learning with Compressed Beliefs
- Attention-gated convolutional neural networks for off-resonance correction of spiral real-time MRI
- Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning
- Exploring Adversarial Robustness of Deep Metric Learning
- Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition
- A Glimpse of Physical Layer Decision Mechanisms: Facts, Challenges, and Remedies
- Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time
- On Topology Optimization and Routing in Integrated Access and Backhaul Networks: A Genetic Algorithm-based Approach
- Reinforcement Learning for IoT Security: A Comprehensive Survey
- Responsibility Management through Responsibility Networks
- Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization
- Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS
- Naturalizing Neuromorphic Vision Event Streams Using GANs
- Double-descent curves in neural networks: a new perspective using Gaussian processes
- Estimating Nonplanar Flow from 2D Motion-blurred Widefield Microscopy Images via Deep Learning
- Learning by Turning: Neural Architecture Aware Optimisation
- Multi-Texture GAN: Exploring the Multi-Scale Texture Translation for Brain MR Images
- Error-driven Pruning of Language Models for Virtual Assistants
- Large-Scale Meta-Learning with Continual Trajectory Shifting
- Why Talking about ethics is not enough: a proposal for Fintech's AI ethics
- Efficient Designs of SLOPE Penalty Sequences in Finite Dimension
- Reversible Action Design for Combinatorial Optimization with Reinforcement Learning
- Sample Efficient Subspace-based Representations for Nonlinear Meta-Learning
- Knowledge Graph Embedding using Graph Convolutional Networks with Relation-Aware Attention
- Improved Bengali Image Captioning via deep convolutional neural network based encoder-decoder model
- Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
- Relation-aware Graph Attention Model With Adaptive Self-adversarial Training
- Partial Disclosure of Private Dependencies in Privacy Preserving Planning
- Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression
- Private learning implies quantum stability
- Adversarial Attack on Network Embeddings via Supervised Network Poisoning
- Distributed Second Order Methods with Fast Rates and Compressed Communication
- ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations
- On the Equilibrium Elicitation of Markov Games Through Information Design
- indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian Languages
- A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularization
- Manifold Density Estimation via Generalized Dequantization
- Perceptually Constrained Adversarial Attacks
- Parametric Optimization of Violin Top Plates using Machine Learning
- Multi-Objective Meta Learning
- Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environment
- Sliced Multi-Marginal Optimal Transport
- Comprehensive Comparative Study of Multi-Label Classification Methods
- A New Algorithm for Hidden Markov Models Learning Problem
- Machine Learning Methods for the Design and Operation of Liquid Rocket Engines -- Research Activities at the DLR Institute of Space Propulsion
- CATE: Computation-aware Neural Architecture Encoding with Transformers
- Healing Products of Gaussian Processes
- Domain Adversarial Reinforcement Learning
- Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
- Decentralized Riemannian Gradient Descent on the Stiefel Manifold
- New methods for metastimuli: architecture, embeddings, and neural network optimization
- Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses
- Exploiting Shared Representations for Personalized Federated Learning
- Model-Agnostic Graph Regularization for Few-Shot Learning
- Tight lower bounds for Dynamic Time Warping
- TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
- Costly Features Classification using Monte Carlo Tree Search
- Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices
- A Forward Backward Greedy approach for Sparse Multiscale Learning
- Fast Monocular Hand Pose Estimation on Embedded Systems
- NeRF--: Neural Radiance Fields Without Known Camera Parameters
- Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss
- Achieving Efficiency in Black Box Simulation of Distribution Tails with Self-structuring Importance Samplers
- Learning Intents behind Interactions with Knowledge Graph for Recommendation
- Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients
- Connecting Interpretability and Robustness in Decision Trees through Separation
- Adversarial defense for automatic speaker verification by cascaded self-supervised learning models
- Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
- Robust Lane Detection via Expanded Self Attention
- Model-free Representation Learning and Exploration in Low-rank MDPs