
-
Sherpa: Robust Hyperparameter Optimization for Machine Learning
Sherpa is a hyperparameter optimization library for machine learning mod...
read it
-
A Study on Graph-Structured Recurrent Neural Networks and Sparsification with Application to Epidemic Forecasting
We study epidemic forecasting on real-world health data by a graph-struc...
read it
-
Probabilistic Kernel Support Vector Machines
We propose a probabilistic enhancement of standard kernel Support Vecto...
read it
-
Learning from Learning Machines: Optimisation, Rules, and Social Norms
There is an analogy between machine learning systems and economic entiti...
read it
-
Obtaining Faithful Interpretations from Compositional Neural Networks
Neural module networks (NMNs) are a popular approach for modeling compos...
read it
-
Extreme Classification via Adversarial Softmax Approximation
Training a classifier over a large number of classes, known as 'extreme ...
read it
-
Tightening Bounds for Variational Inference by Revisiting Perturbation Theory
Variational inference has become one of the most widely used methods in ...
read it
-
Improving Inference for Neural Image Compression
We consider the problem of lossy image compression with deep latent vari...
read it
-
Image Augmentations for GAN Training
Data augmentations have been widely studied to improve the accuracy and ...
read it
-
SPLASH: Learnable Activation Functions for Improving Accuracy and Adversarial Robustness
We introduce SPLASH units, a class of learnable activation functions sho...
read it
-
Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning
Reinforcement learning algorithms can show strong variation in performan...
read it
-
Neuromodulated Patience for Robot and Self-Driving Vehicle Navigation
Robots and self-driving vehicles face a number of challenges when naviga...
read it
-
Image Reconstruction with Predictive Filter Flow
We propose a simple, interpretable framework for solving a wide range of...
read it
-
Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
Leveraging synthetically rendered data offers great potential to improve...
read it
-
Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Nets
Deep neural nets (DNNs) compression is crucial for adaptation to mobile ...
read it
-
Multi-View Collaborative Network Embedding
Real-world networks often exist with multiple views, where each view des...
read it
-
Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
In Autonomous Vehicles (AVs), one fundamental pillar is perception, whic...
read it
-
Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling
Localizing thoracic diseases on chest X-ray plays a critical role in cli...
read it
-
AnatomyNet: Deep 3D Squeeze-and-excitation U-Nets for fast and fully automated whole-volume anatomical segmentation
Radiation therapy (RT) is a common treatment for head and neck (HaN) can...
read it
-
Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency
As deep reinforcement learning (RL) is applied to more tasks, there is a...
read it
-
Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
The edge computing paradigm places compute-capable devices - edge server...
read it
-
Active Bayesian Assessment for Black-Box Classifiers
Recent advances in machine learning have led to increased deployment of ...
read it
-
Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation
Monocular estimation of 3d human pose has attracted increased attention ...
read it
-
Split Computing for Complex Object Detectors: Challenges and Preliminary Results
Following the trends of mobile and edge computing for DNN models, an int...
read it
-
Memory capacity of neural networks with threshold and ReLU activations
Overwhelming theoretical and empirical evidence shows that mildly overpa...
read it
-
Sparse Representations for Object and Ego-motion Estimation in Dynamic Scenes
Dynamic scenes that contain both object motion and egomotion are a chall...
read it
-
Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
Training activation quantized neural networks involves minimizing a piec...
read it
-
Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications
Representing entities and relations in an embedding space is a well-stud...
read it
-
Bounding the Complexity of Formally Verifying Neural Networks: A Geometric Approach
In this paper, we consider the computational complexity of formally veri...
read it
-
Curiosity-Driven Multi-Criteria Hindsight Experience Replay
Dealing with sparse rewards is a longstanding challenge in reinforcement...
read it
-
Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts
We develop new representations and algorithms for three-dimensional (3D)...
read it
-
Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks
Quantized deep neural networks (QDNNs) are attractive due to their much ...
read it
-
Neural Multi-Scale Self-Supervised Registration for Echocardiogram Dense Tracking
Echocardiography has become routinely used in the diagnosis of cardiomyo...
read it
-
PyCARL: A PyNN Interface for Hardware-Software Co-Simulation of Spiking Neural Network
We present PyCARL, a PyNN-based common Python programming interface for ...
read it
-
Continuous Representation of Molecules Using Graph Variational Autoencoder
In order to continuously represent molecules, we propose a generative mo...
read it
-
Universal halting times in optimization and machine learning
The authors present empirical distributions for the halting time (measur...
read it
-
DeepLung: 3D Deep Convolutional Nets for Automated Pulmonary Nodule Detection and Classification
In this work, we present a fully automated lung CT cancer diagnosis syst...
read it
-
Square-Contact Representations of Partial 2-Trees and Triconnected Simply-Nested Graphs
A square-contact representation of a planar graph G=(V,E) maps vertices ...
read it
-
Weakly Supervised Action Localization by Sparse Temporal Pooling Network
We propose a weakly supervised temporal action localization algorithm on...
read it
-
Improving Malware Detection Accuracy by Extracting Icon Information
Detecting PE malware files is now commonly approached using statistical ...
read it
-
Adversarial Deep Structured Nets for Mass Segmentation from Mammograms
Mass segmentation provides effective morphological features which are im...
read it
-
Mondrian Processes for Flow Cytometry Analysis
Analysis of flow cytometry data is an essential tool for clinical diagno...
read it
-
Generating Natural Adversarial Examples
Due to their complex nature, it is hard to characterize the ways in whic...
read it
-
Learning Infinite RBMs with Frank-Wolfe
In this work, we propose an infinite restricted Boltzmann machine (RBM),...
read it
-
Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
Mammogram classification is directly related to computer-aided diagnosis...
read it
-
Information Design in Crowdfunding under Thresholding Policies
In crowdfunding, an entrepreneur often has to decide how to disclose the...
read it
-
Regulating Highly Automated Robot Ecologies: Insights from Three User Studies
Highly automated robot ecologies (HARE), or societies of independent aut...
read it
-
A Self-Driving Robot Using Deep Convolutional Neural Networks on Neuromorphic Hardware
Neuromorphic computing is a promising solution for reducing the size, we...
read it
-
Relational Learning and Feature Extraction by Querying over Heterogeneous Information Networks
Many real world systems need to operate on heterogeneous information net...
read it
-
Energy-Based Spherical Sparse Coding
In this paper, we explore an efficient variant of convolutional sparse c...
read it