University of California, Irvine

research

∙ 05/08/2020

Sherpa: Robust Hyperparameter Optimization for Machine Learning

Sherpa is a hyperparameter optimization library for machine learning mod...

Lars Hertel, et al. ∙

research

∙ 03/24/2021

Quantum Mechanics and Machine Learning Synergies: Graph Attention Neural Networks to Predict Chemical Reactivity

There is a lack of scalable quantitative measures of reactivity for func...

Mohammadamin Tavakoli, et al. ∙

research

∙ 01/02/2022

Rxn Hypergraph: a Hypergraph Attention Model for Chemical Reaction Representation

It is fundamental for science and technology to be able to predict chemi...

Mohammadamin Tavakoli, et al. ∙

research

∙ 06/21/2022

Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discovery

This paper revisits datasets and evaluation criteria for Symbolic Regres...

Yoshitomo Matsubara, et al. ∙

research

∙ 02/13/2019

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...

Zhijian Li, et al. ∙

research

∙ 11/11/2021

Spatio-Temporal Scene-Graph Embedding for Autonomous Vehicle Collision Prediction

In autonomous vehicles (AVs), early warning systems rely on collision pr...

Arnav V. Malawade, et al. ∙

research

∙ 04/14/2019

Probabilistic Kernel Support Vector Machines

We propose a probabilistic enhancement of standard kernel Support Vecto...

Yongxin Chen, et al. ∙

research

∙ 12/29/2019

Learning from Learning Machines: Optimisation, Rules, and Social Norms

There is an analogy between machine learning systems and economic entiti...

Travis LaCroix, et al. ∙

research

∙ 05/02/2020

Obtaining Faithful Interpretations from Compositional Neural Networks

Neural module networks (NMNs) are a popular approach for modeling compos...

Sanjay Subramanian, et al. ∙

research

∙ 08/05/2021

FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention

We propose FMMformers, a class of efficient and flexible transformers in...

Tan M. Nguyen, et al. ∙

research

∙ 02/15/2020

Extreme Classification via Adversarial Softmax Approximation

Training a classifier over a large number of classes, known as 'extreme ...

Robert Bamler, et al. ∙

research

∙ 09/30/2019

Tightening Bounds for Variational Inference by Revisiting Perturbation Theory

Variational inference has become one of the most widely used methods in ...

Robert Bamler, et al. ∙

research

∙ 06/07/2020

Improving Inference for Neural Image Compression

We consider the problem of lossy image compression with deep latent vari...

Yibo Yang, et al. ∙

research

∙ 06/04/2020

Image Augmentations for GAN Training

Data augmentations have been widely studied to improve the accuracy and ...

Zhengli Zhao, et al. ∙

research

∙ 03/26/2022

Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension

Question answering (QA) is a fundamental means to facilitate assessment ...

Ying Xu, et al. ∙

research

∙ 06/16/2020

SPLASH: Learnable Activation Functions for Improving Accuracy and Adversarial Robustness

We introduce SPLASH units, a class of learnable activation functions sho...

Mohammadamin Tavakoli, et al. ∙

research

∙ 09/21/2021

Assured Neural Network Architectures for Control and Identification of Nonlinear Systems

In this paper, we consider the problem of automatically designing a Rect...

James Ferlez, et al. ∙

research

∙ 07/29/2020

Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning

Reinforcement learning algorithms can show strong variation in performan...

Lars Hertel, et al. ∙

research

∙ 06/07/2022

MIRNF: Medical Image Registration via Neural Fields

Image registration is widely used in medical image analysis to provide s...

Shanlin Sun, et al. ∙

research

∙ 09/05/2021

Modular Framework for Visuomotor Language Grounding

Natural language instruction following tasks serve as a valuable test-be...

Kolby Nottingham, et al. ∙

research

∙ 07/26/2022

A Two-Stage Efficient 3-D CNN Framework for EEG Based Emotion Recognition

This paper proposes a novel two-stage framework for emotion recognition ...

Ye Qiao, et al. ∙

research

∙ 09/14/2019

Neuromodulated Patience for Robot and Self-Driving Vehicle Navigation

Robots and self-driving vehicles face a number of challenges when naviga...

Jinwei Xing, et al. ∙

research

∙ 03/02/2020

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 ...

Thu Dinh, et al. ∙

research

∙ 06/06/2022

Deep Learning Models of the Discrete Component of the Galactic Interstellar Gamma-Ray Emission

A significant point-like component from the small scale (or discrete) st...

Alexander Shmakov, et al. ∙

research

∙ 11/28/2018

Image Reconstruction with Predictive Filter Flow

We propose a simple, interpretable framework for solving a wide range of...

Shu Kong, et al. ∙

research

∙ 02/27/2020

Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation

Leveraging synthetically rendered data offers great potential to improve...

Yunhan Zhao, et al. ∙

research

∙ 05/17/2020

Multi-View Collaborative Network Embedding

Real-world networks often exist with multiple views, where each view des...

Sezin Kircali Ata, et al. ∙

research

∙ 06/29/2021

Diff2Dist: Learning Spectrally Distinct Edge Functions, with Applications to Cell Morphology Analysis

We present a method for learning "spectrally descriptive" edge weights f...

Cory Braker Scott, et al. ∙

research

∙ 08/02/2021

Recurrent Mask Refinement for Few-Shot Medical Image Segmentation

Although having achieved great success in medical image segmentation, de...

Hao Tang, et al. ∙

research

∙ 07/16/2019

Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving

In Autonomous Vehicles (AVs), one fundamental pillar is perception, whic...

Yulong Cao, et al. ∙

research

∙ 05/29/2020

Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling

Localizing thoracic diseases on chest X-ray plays a critical role in cli...

Wenwu Ye, et al. ∙

research

∙ 03/16/2022

Diffusion Probabilistic Modeling for Video Generation

Denoising diffusion probabilistic models are a promising new class of ge...

Ruihan Yang, et al. ∙

research

∙ 08/15/2018

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...

Wentao Zhu, et al. ∙

research

∙ 12/23/2019

Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency

As deep reinforcement learning (RL) is applied to more tasks, there is a...

Piyush Gupta, et al. ∙

research

∙ 07/31/2020

Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks

The edge computing paradigm places compute-capable devices - edge server...

Yoshitomo Matsubara, et al. ∙

research

∙ 09/03/2021

Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach

While conventional reinforcement learning focuses on designing agents th...

Xiaowu Sun, et al. ∙

research

∙ 02/16/2020

Active Bayesian Assessment for Black-Box Classifiers

Recent advances in machine learning have led to increased deployment of ...

Disi Ji, et al. ∙

research

∙ 04/07/2020

Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation

Monocular estimation of 3d human pose has attracted increased attention ...

Zhe Wang, et al. ∙

research

∙ 10/11/2021

Safe Model-Based Reinforcement Learning Using Robust Control Barrier Functions

Reinforcement Learning (RL) is effective in many scenarios. However, it ...

Yousef Emam, et al. ∙

research

∙ 07/27/2020

Split Computing for Complex Object Detectors: Challenges and Preliminary Results

Following the trends of mobile and edge computing for DNN models, an int...

Yoshitomo Matsubara, et al. ∙

research

∙ 01/20/2020

Memory capacity of neural networks with threshold and ReLU activations

Overwhelming theoretical and empirical evidence shows that mildly overpa...

Roman Vershynin, et al. ∙

research

∙ 07/13/2021

Tourbillon: a Physically Plausible Neural Architecture

In a physical neural system, backpropagation is faced with a number of o...

Mohammadamin Tavakoli, et al. ∙

research

∙ 12/11/2021

OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion

Muscle-actuated control is a research topic of interest spanning differe...

Vittorio La Barbera, et al. ∙

research

∙ 03/09/2019

Sparse Representations for Object and Ego-motion Estimation in Dynamic Scenes

Dynamic scenes that contain both object motion and egomotion are a chall...

Hirak J Kashyap, et al. ∙

research

∙ 03/13/2019

Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets

Training activation quantized neural networks involves minimizing a piec...

Penghang Yin, et al. ∙

research

∙ 05/02/2019

Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications

Representing entities and relations in an embedding space is a well-stud...

Pouya Pezeshkpour, et al. ∙

research

∙ 07/06/2021

On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving

After the 2017 TuSimple Lane Detection Challenge, its evaluation based o...

Takami Sato, et al. ∙

research

∙ 04/06/2021

Safe-by-Repair: A Convex Optimization Approach for Repairing Unsafe Two-Level Lattice Neural Network Controllers

In this paper, we consider the problem of repairing a data-trained Recti...

Ulices Santa Cruz, et al. ∙

research

∙ 09/29/2021

Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration

An increasingly common use case for machine learning models is augmentin...

Gavin Kerrigan, et al. ∙

research

∙ 11/07/2021

High-order joint embedding for multi-level link prediction

Link prediction infers potential links from observed networks, and is on...

Yubai Yuan, et al. ∙

University of California, Irvine

Featured Researchers