Search Results for author:
Found 48 papers, 11 papers with code
A Neuromorphic Approach to Obstacle Avoidance in Robot Manipulation
To investigate the utility of brain-inspired sensing and data processing, we developed a neuromorphic approach to obstacle avoidance on a camera-equipped manipulator.
Sanity Checks for Explanation Uncertainty
Explanations for machine learning models can be hard to interpret or be wrong.
Uncertainty Quantification for Gradient-based Explanations in Neural Networks
By computing the coefficient of variation of these distributions, we evaluate the confidence in the explanation and determine that the explanations generated using Guided Backpropagation have low uncertainty associated with them.
Uncertainty Quantification for cross-subject Motor Imagery classification
We applied a variety of Uncertainty Quantification methods to predict misclassifications for a Motor Imagery Brain Computer Interface.
Transferring BCI models from calibration to control: Observing shifts in EEG features
We demonstrate a new paradigm containing a standard calibration session and a novel BCI control session based on EMG.
Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation
Recommendation systems, for documents, have become tools to find relevant content on the Web.
ChatGPT Prompting Cannot Estimate Predictive Uncertainty in High-Resource Languages
This paper aims to join the growing literature regarding ChatGPT's abilities by focusing on its performance in high-resource languages and on its capacity to predict its answers' accuracy by giving a confidence level.
Sanity Checks for Saliency Methods Explaining Object Detectors
Adebayo et al.'s work on evaluating saliency methods for classification models illustrate certain explanation methods fail the model and data randomization tests.
DExT: Detector Explanation Toolkit
State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations.
Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models
Trusting the predictions of deep learning models in safety critical settings such as the medical domain is still not a viable option.
A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation
We observed that Deep Ensembles out perform Flipout model in OOD detection with greater AUROC scores for both datasets.
Comparison of Uncertainty Quantification with Deep Learning in Time Series Regression
Increasingly high-stakes decisions are made using neural networks in order to make predictions.
Machine Learning Students Overfit to Overfitting
Overfitting and generalization is an important concept in Machine Learning as only models that generalize are interesting for general applications.
A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement
Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best.
Self-supervised Learning for Sonar Image Classification
Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets.
Feature Disentanglement of Robot Trajectories
Modeling trajectories generated by robot joints is complex and required for high level activities like trajectory generation, clustering, and classification.
Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning
Out of distribution detection for RL is generally not well covered in the literature, and there is a lack of benchmarks for this task.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+2
Exploring the Limits of Epistemic Uncertainty Quantification in Low-Shot Settings
Uncertainty quantification in neural network promises to increase safety of AI systems, but it is not clear how performance might vary with the training set size.
The VVAD-LRS3 Dataset for Visual Voice Activity Detection
With a Convolutional Neural Network Long Short Term Memory (CNN LSTM) on facial images an accuracy of 92% was reached on the test set.
Teaching Uncertainty Quantification in Machine Learning through Use Cases
Uncertainty in machine learning is not generally taught as general knowledge in Machine Learning course curricula.
The Marine Debris Dataset for Forward-Looking Sonar Semantic Segmentation
This paper presents a novel dataset for marine debris segmentation collected using a Forward Looking Sonar (FLS).
Deep Reinforcement Learning for Continuous Docking Control of Autonomous Underwater Vehicles: A Benchmarking Study
Docking control of an autonomous underwater vehicle (AUV) is a task that is integral to achieving persistent long term autonomy.
Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty
Application of underwater robots are on the rise, most of them are dependent on sonar for underwater vision, but the lack of strong perception capabilities limits them in this task.
Pre-trained Models for Sonar Images
Machine learning and neural networks are now ubiquitous in sonar perception, but it lags behind the computer vision field due to the lack of data and pre-trained models specifically for sonar images.
I Find Your Lack of Uncertainty in Computer Vision Disturbing
Neural networks are used for many real world applications, but often they have problems estimating their own confidence.
Are Gradient-based Saliency Maps Useful in Deep Reinforcement Learning?
It is being proven to what extent the algorithms can be used in the area of Reinforcement learning.
Automatic Detection and Classification of Tick-borne Skin Lesions using Deep Learning
Around the globe, ticks are the culprit of transmitting a variety of bacterial, viral and parasitic diseases.
Unsupervised Difficulty Estimation with Action Scores
Evaluating difficulty and biases in machine learning models has become of extreme importance as current models are now being applied in real-world situations.
Black-Box Optimization of Object Detector Scales
In this work, we propose the use of Black-box optimization methods to tune the prior/default box scales in Faster R-CNN and SSD, using Bayesian Optimization, SMAC, and CMA-ES.
Perception for Autonomous Systems (PAZ)
In this paper we introduce the Perception for Autonomous Systems (PAZ) software library.
Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation
Through our experiments, we show a significant reduction in the GFLOPS required to model uncertainty, compared to Monte Carlo DropConnect, with marginal trade-off in performance.
Can Reinforcement Learning for Continuous Control Generalize Across Physics Engines?
There are multiple algorithms that solve the task in a physics engine based environment but there is no work done so far to understand if the RL algorithms can generalize across physics engines.
Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!
In this paper we show that Bayesian Neural Networks, as approximated using MC-Dropout, MC-DropConnect, or an Ensemble, are able to model the aleatoric uncertainty in facial emotion recognition, and produce output probabilities that are closer to what a human expects.
Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds
Deep learning models are extensively used in various safety critical applications.
Results from the Robocademy ITN: Autonomy, Disturbance Rejection and Perception for Advanced Marine Robotics
Marine and Underwater resources are important part of the economy of many countries.
Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification
Fast estimates of model uncertainty are required for many robust robotics applications.
Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition
SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation.
Learning Objectness from Sonar Images for Class-Independent Object Detection
Detecting novel objects without class information is not trivial, as it is difficult to generalize from a small training set.
Deep Neural Networks for Marine Debris Detection in Sonar Images
Proper waste disposal and recycling is a must in any sustainable community, and in many coastal areas there is significant water pollution in the form of floating or submerged garbage.
Implementing Noise with Hash functions for Graphics Processing Units
We propose a modification to Perlin noise which use computable hash functions instead of textures as lookup tables.
Graphics
Modeling and Soft-fault Diagnosis of Underwater Thrusters with Recurrent Neural Networks
Noncritical soft-faults and model deviations are a challenge for Fault Detection and Diagnosis (FDD) of resident Autonomous Underwater Vehicles (AUVs).
Improving Predictive Uncertainty Estimation using Dropout -- Hamiltonian Monte Carlo
Estimating predictive uncertainty is crucial for many computer vision tasks, from image classification to autonomous driving systems.
Image Captioning and Classification of Dangerous Situations
Current robot platforms are being employed to collaborate with humans in a wide range of domestic and industrial tasks.
Real-time Convolutional Neural Networks for Emotion and Gender Classification
In this paper we propose an implement a general convolutional neural network (CNN) building framework for designing real-time CNNs.
Best Practices in Convolutional Networks for Forward-Looking Sonar Image Recognition
In this work, we evaluate three common decisions that need to be made by a CNN designer, namely the performance of transfer learning, the effect of object/image size and the relation between training set size.
Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks
In this work we develop a Convolutional Neural Network that can reliably score objectness of image windows in forward-looking sonar images and by thresholding objectness, we generate detection proposals.
Real-time convolutional networks for sonar image classification in low-power embedded systems
Deep Neural Networks have impressive classification performance, but this comes at the expense of significant computational resources at inference time.
Improving Sonar Image Patch Matching via Deep Learning
Matching sonar images with high accuracy has been a problem for a long time, as sonar images are inherently hard to model due to reflections, noise and viewpoint dependence.
