Search Results for author: Daniela Rus

Found 101 papers, 35 papers with code

The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits

no code implementations ICML 2020 Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu

We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model to govern simulated and real-world control tasks.

reinforcement-learning Reinforcement Learning (RL)

Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control

2 code implementations ICML 2020 Jie Xu, Yunsheng Tian, Pingchuan Ma, Daniela Rus, Shinjiro Sueda, Wojciech Matusik

Many real-world control problems involve conflicting objectives where we desire a dense and high-quality set of control policies that are optimal for different objective preferences (called Pareto-optimal).

Multi-Objective Reinforcement Learning reinforcement-learning

Hypergraph-Transformer (HGT) for Interactive Event Prediction in Laparoscopic and Robotic Surgery

no code implementations3 Feb 2024 Lianhao Yin, Yutong Ban, Jennifer Eckhoff, Ozanan Meireles, Daniela Rus, Guy Rosman

Understanding and anticipating intraoperative events and actions is critical for intraoperative assistance and decision-making during minimally invasive surgery.

Decision Making Knowledge Graphs

Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels

no code implementations25 Jan 2024 Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu

Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures, that surpass the performance of classical CNNs, by a considerable scalability and accuracy margin.

Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields

no code implementations18 Jan 2024 Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu

In this study, we present evidence suggesting that depthwise convolutional kernels are effectively replicating the structural intricacies of the biological receptive fields observed in the mammalian retina.

Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?

no code implementations21 Nov 2023 Mónika Farsang, Mathias Lechner, David Lung, Ramin Hasani, Daniela Rus, Radu Grosu

In this work we aim to determine the impact of using chemical synapses compared to electrical synapses, in both sparse and all-to-all connected networks.

Autonomous Driving

Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models

no code implementations26 Oct 2023 Tsun-Hsuan Wang, Alaa Maalouf, Wei Xiao, Yutong Ban, Alexander Amini, Guy Rosman, Sertac Karaman, Daniela Rus

As autonomous driving technology matures, end-to-end methodologies have emerged as a leading strategy, promising seamless integration from perception to control via deep learning.

Autonomous Driving Data Augmentation

Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

no code implementations5 Oct 2023 Neehal Tumma, Mathias Lechner, Noel Loo, Ramin Hasani, Daniela Rus

In this work, we explore the application of recurrent neural networks to tasks of this nature and understand how a parameterization of their recurrent connectivity influences robustness in closed-loop settings.

Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions

no code implementations6 Sep 2023 Wei Xiao, Ross Allen, Daniela Rus

To address these challenges, we incorporate higher-order CBFs into neural ordinary differential equation-based learning models as differentiable CBFs to guarantee safety for non-affine control systems.

Autonomous Driving Imitation Learning

Follow Anything: Open-set detection, tracking, and following in real-time

1 code implementation10 Aug 2023 Alaa Maalouf, Ninad Jadhav, Krishna Murthy Jatavallabhula, Makram Chahine, Daniel M. Vogt, Robert J. Wood, Antonio Torralba, Daniela Rus

We demonstrate FAn on a real-world robotic system (a micro aerial vehicle) and report its ability to seamlessly follow the objects of interest in a real-time control loop.

Capsa: A Unified Framework for Quantifying Risk in Deep Neural Networks

no code implementations1 Aug 2023 Sadhana Lolla, Iaroslav Elistratov, Alejandro Perez, Elaheh Ahmadi, Daniela Rus, Alexander Amini

We validate capsa by implementing state-of-the-art uncertainty estimation algorithms within the capsa framework and benchmarking them on complex perception datasets.

Benchmarking

Efficient automatic design of robots

no code implementations5 Jun 2023 David Matthews, Andrew Spielberg, Daniela Rus, Sam Kriegman, Josh Bongard

Robots are notoriously difficult to design because of complex interdependencies between their physical structure, sensory and motor layouts, and behavior.

Evolutionary Algorithms

SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

no code implementations31 May 2023 Wei Xiao, Tsun-Hsuan Wang, Chuang Gan, Daniela Rus

Diffusion model-based approaches have shown promise in data-driven planning, but there are no safety guarantees, thus making it hard to be applied for safety-critical applications.

Denoising

On the Size and Approximation Error of Distilled Sets

no code implementations23 May 2023 Alaa Maalouf, Murad Tukan, Noel Loo, Ramin Hasani, Mathias Lechner, Daniela Rus

Despite significant empirical progress in recent years, there is little understanding of the theoretical limitations/guarantees of dataset distillation, specifically, what excess risk is achieved by distillation compared to the original dataset, and how large are distilled datasets?

regression

AutoCoreset: An Automatic Practical Coreset Construction Framework

1 code implementation19 May 2023 Alaa Maalouf, Murad Tukan, Vladimir Braverman, Daniela Rus

A coreset is a tiny weighted subset of an input set, that closely resembles the loss function, with respect to a certain set of queries.

Studying the Impact of Semi-Cooperative Drivers on Overall Highway Flow

no code implementations23 Apr 2023 Noam Buckman, Sertac Karaman, Daniela Rus

Yet the overall impact on traffic flow for this new class of planners remain to be understood.

Autonomous Driving

Infrastructure-based End-to-End Learning and Prevention of Driver Failure

no code implementations21 Mar 2023 Noam Buckman, Shiva Sreeram, Mathias Lechner, Yutong Ban, Ramin Hasani, Sertac Karaman, Daniela Rus

FailureNet observes the poses of vehicles as they approach an intersection and detects whether a failure is present in the autonomy stack, warning cross-traffic of potentially dangerous drivers.

Autonomous Vehicles

Provable Data Subset Selection For Efficient Neural Network Training

1 code implementation9 Mar 2023 Murad Tukan, Samson Zhou, Alaa Maalouf, Daniela Rus, Vladimir Braverman, Dan Feldman

In this paper, we introduce the first algorithm to construct coresets for \emph{RBFNNs}, i. e., small weighted subsets that approximate the loss of the input data on any radial basis function network and thus approximate any function defined by an \emph{RBFNN} on the larger input data.

Efficient Neural Network

Learned Risk Metric Maps for Kinodynamic Systems

1 code implementation28 Feb 2023 Ross Allen, Wei Xiao, Daniela Rus

We present Learned Risk Metric Maps (LRMM) for real-time estimation of coherent risk metrics of high dimensional dynamical systems operating in unstructured, partially observed environments.

Dataset Distillation with Convexified Implicit Gradients

2 code implementations13 Feb 2023 Noel Loo, Ramin Hasani, Mathias Lechner, Daniela Rus

We propose a new dataset distillation algorithm using reparameterization and convexification of implicit gradients (RCIG), that substantially improves the state-of-the-art.

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation

1 code implementation2 Feb 2023 Noel Loo, Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus

We show that both theoretically and empirically, reconstructed images tend to "outliers" in the dataset, and that these reconstruction attacks can be used for \textit{dataset distillation}, that is, we can retrain on reconstructed images and obtain high predictive accuracy.

Reconstruction Attack

Towards Cooperative Flight Control Using Visual-Attention

no code implementations21 Dec 2022 Lianhao Yin, Makram Chahine, Tsun-Hsuan Wang, Tim Seyde, Chao Liu, Mathias Lechner, Ramin Hasani, Daniela Rus

We propose an air-guardian system that facilitates cooperation between a pilot with eye tracking and a parallel end-to-end neural control system.

Feature Importance

Solving Continuous Control via Q-learning

1 code implementation22 Oct 2022 Tim Seyde, Peter Werner, Wilko Schwarting, Igor Gilitschenski, Martin Riedmiller, Daniela Rus, Markus Wulfmeier

While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the associated high-dimensional action spaces.

Continuous Control Multi-agent Reinforcement Learning +1

Efficient Dataset Distillation Using Random Feature Approximation

2 code implementations21 Oct 2022 Noel Loo, Ramin Hasani, Alexander Amini, Daniela Rus

Dataset distillation compresses large datasets into smaller synthetic coresets which retain performance with the aim of reducing the storage and computational burden of processing the entire dataset.

Dataset Condensation regression

Pruning by Active Attention Manipulation

no code implementations20 Oct 2022 Zahra Babaiee, Lucas Liebenwein, Ramin Hasani, Daniela Rus, Radu Grosu

On CIFAR-10 dataset, without requiring a pre-trained baseline network, we obtain 1. 02% and 1. 19% accuracy gain and 52. 3% and 54% parameters reduction, on ResNet56 and ResNet110, respectively.

Interpreting Neural Policies with Disentangled Tree Representations

no code implementations13 Oct 2022 Tsun-Hsuan Wang, Wei Xiao, Tim Seyde, Ramin Hasani, Daniela Rus

The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning.

Disentanglement

On the Forward Invariance of Neural ODEs

no code implementations10 Oct 2022 Wei Xiao, Tsun-Hsuan Wang, Ramin Hasani, Mathias Lechner, Yutong Ban, Chuang Gan, Daniela Rus

We propose a new method to ensure neural ordinary differential equations (ODEs) satisfy output specifications by using invariance set propagation.

Autonomous Vehicles Collision Avoidance +2

Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap

no code implementations9 Oct 2022 Mathias Lechner, Ramin Hasani, Alexander Amini, Tsun-Hsuan Wang, Thomas A. Henzinger, Daniela Rus

Our results imply that the causality gap can be solved in situation one with our proposed training guideline with any modern network architecture, whereas achieving out-of-distribution generalization (situation two) requires further investigations, for instance, on data diversity rather than the model architecture.

Autonomous Driving Image Classification +1

Liquid Structural State-Space Models

1 code implementation26 Sep 2022 Ramin Hasani, Mathias Lechner, Tsun-Hsuan Wang, Makram Chahine, Alexander Amini, Daniela Rus

A proper parametrization of state transition matrices of linear state-space models (SSMs) followed by standard nonlinearities enables them to efficiently learn representations from sequential data, establishing the state-of-the-art on a large series of long-range sequence modeling benchmarks.

Heart rate estimation Long-range modeling +3

Deep Learning on Home Drone: Searching for the Optimal Architecture

1 code implementation21 Sep 2022 Alaa Maalouf, Yotam Gurfinkel, Barak Diker, Oren Gal, Daniela Rus, Dan Feldman

We suggest the first system that runs real-time semantic segmentation via deep learning on a weak micro-computer such as the Raspberry Pi Zero v2 (whose price was \$15) attached to a toy-drone.

Real-Time Semantic Segmentation

BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling

no code implementations25 Jun 2022 Yechao Bai, Xiaogang Wang, Marcelo H. Ang Jr, Daniela Rus

The learning and aggregation of multi-scale features are essential in empowering neural networks to capture the fine-grained geometric details in the point cloud upsampling task.

Entangled Residual Mappings

no code implementations2 Jun 2022 Mathias Lechner, Ramin Hasani, Zahra Babaiee, Radu Grosu, Daniela Rus, Thomas A. Henzinger, Sepp Hochreiter

Residual mappings have been shown to perform representation learning in the first layers and iterative feature refinement in higher layers.

Inductive Bias Representation Learning

Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning

no code implementations15 Apr 2022 Mathias Lechner, Alexander Amini, Daniela Rus, Thomas A. Henzinger

However, the improved robustness does not come for free but rather is accompanied by a decrease in overall model accuracy and performance.

Adversarial Robustness Autonomous Driving +2

End-to-End Sensitivity-Based Filter Pruning

no code implementations15 Apr 2022 Zahra Babaiee, Lucas Liebenwein, Ramin Hasani, Daniela Rus, Radu Grosu

Moreover, by training the pruning scores of all layers simultaneously our method can account for layer interdependencies, which is essential to find a performant sparse sub-network.

Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models

no code implementations5 Apr 2022 Jose L. Vazquez, Alexander Liniger, Wilko Schwarting, Daniela Rus, Luc van Gool

Fundamental to the success of our method is the design of a novel multi-agent policy network that can steer a vehicle given the state of the surrounding agents and the map information.

motion prediction

Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving

no code implementations4 Mar 2022 Wei Xiao, Tsun-Hsuan Wang, Makram Chahine, Alexander Amini, Ramin Hasani, Daniela Rus

They are interpretable at scale, achieve great test performance under limited training data, and are safety guaranteed in a series of autonomous driving scenarios such as lane keeping and obstacle avoidance.

Autonomous Driving

Concept Graph Neural Networks for Surgical Video Understanding

no code implementations27 Feb 2022 Yutong Ban, Jennifer A. Eckhoff, Thomas M. Ward, Daniel A. Hashimoto, Ozanan R. Meireles, Daniela Rus, Guy Rosman

We constantly integrate our knowledge and understanding of the world to enhance our interpretation of what we see.

Video Understanding

BarrierNet: A Safety-Guaranteed Layer for Neural Networks

no code implementations22 Nov 2021 Wei Xiao, Ramin Hasani, Xiao Li, Daniela Rus

This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems.

Model Based Control of Soft Robots: A Survey of the State of the Art and Open Challenges

no code implementations4 Oct 2021 Cosimo Della Santina, Christian Duriez, Daniela Rus

Continuum soft robots are mechanical systems entirely made of continuously deformable elements.

Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition

2 code implementations NeurIPS 2021 Lucas Liebenwein, Alaa Maalouf, Oren Gal, Dan Feldman, Daniela Rus

We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultaneously achieving the desired overall compression.

Low-rank compression

GoTube: Scalable Stochastic Verification of Continuous-Depth Models

1 code implementation18 Jul 2021 Sophie Gruenbacher, Mathias Lechner, Ramin Hasani, Daniela Rus, Thomas A. Henzinger, Scott Smolka, Radu Grosu

Our algorithm solves a set of global optimization (Go) problems over a given time horizon to construct a tight enclosure (Tube) of the set of all process executions starting from a ball of initial states.

Closed-form Continuous-time Neural Models

1 code implementation25 Jun 2021 Ramin Hasani, Mathias Lechner, Alexander Amini, Lucas Liebenwein, Aaron Ray, Max Tschaikowski, Gerald Teschl, Daniela Rus

To this end, we compute a tightly-bounded approximation of the solution of an integral appearing in LTCs' dynamics, that has had no known closed-form solution so far.

Sentiment Analysis Time Series Prediction

Sparse Flows: Pruning Continuous-depth Models

1 code implementation NeurIPS 2021 Lucas Liebenwein, Ramin Hasani, Alexander Amini, Daniela Rus

Our empirical results suggest that pruning improves generalization for neural ODEs in generative modeling.

Causal Navigation by Continuous-time Neural Networks

1 code implementation NeurIPS 2021 Charles Vorbach, Ramin Hasani, Alexander Amini, Mathias Lechner, Daniela Rus

We evaluate our method in the context of visual-control learning of drones over a series of complex tasks, ranging from short- and long-term navigation, to chasing static and dynamic objects through photorealistic environments.

Imitation Learning

Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation

no code implementations3 Jun 2021 Yechao Bai, Ziyuan Huang, Lyuyu Shen, Hongliang Guo, Marcelo H. Ang Jr, Daniela Rus

Experiment results on two challenging datasets Cityscapes and COCO demonstrate that the RSP head performs competitively on both semantic segmentation and panoptic segmentation with high efficiency.

Panoptic Segmentation Relation +1

Efficient and Robust LiDAR-Based End-to-End Navigation

no code implementations20 May 2021 Zhijian Liu, Alexander Amini, Sibo Zhu, Sertac Karaman, Song Han, Daniela Rus

On the other hand, increasing the robustness of these systems is also critical; however, even estimating the model's uncertainty is very challenging due to the cost of sampling-based methods.

Estimating the State of Epidemics Spreading with Graph Neural Networks

no code implementations10 May 2021 Abhishek Tomy, Matteo Razzanelli, Francesco Di Lauro, Daniela Rus, Cosimo Della Santina

When an epidemic spreads into a population, it is often unpractical or impossible to have a continuous monitoring of all subjects involved.

SUPR-GAN: SUrgical PRediction GAN for Event Anticipation in Laparoscopic and Robotic Surgery

no code implementations10 May 2021 Yutong Ban, Guy Rosman, Jennifer A. Eckhoff, Thomas M. Ward, Daniel A. Hashimoto, Taisei Kondo, Hidekazu Iwaki, Ozanan R. Meireles, Daniela Rus

Comprehension of surgical workflow is the foundation upon which artificial intelligence (AI) and machine learning (ML) holds the potential to assist intraoperative decision-making and risk mitigation.

Decision Making Generative Adversarial Network

Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales

no code implementations17 Apr 2021 Jacob Andreas, Gašper Beguš, Michael M. Bronstein, Roee Diamant, Denley Delaney, Shane Gero, Shafi Goldwasser, David F. Gruber, Sarah de Haas, Peter Malkin, Roger Payne, Giovanni Petri, Daniela Rus, Pratyusha Sharma, Dan Tchernov, Pernille Tønnesen, Antonio Torralba, Daniel Vogt, Robert J. Wood

We posit that machine learning will be the cornerstone of future collection, processing, and analysis of multimodal streams of data in animal communication studies, including bioacoustic, behavioral, biological, and environmental data.

BIG-bench Machine Learning Sentence +1

Low-Regret Active learning

no code implementations6 Apr 2021 Cenk Baykal, Lucas Liebenwein, Dan Feldman, Daniela Rus

We develop an online learning algorithm for identifying unlabeled data points that are most informative for training (i. e., active learning).

Active Learning Informativeness

TransCenter: Transformers with Dense Representations for Multiple-Object Tracking

2 code implementations28 Mar 2021 Yihong Xu, Yutong Ban, Guillaume Delorme, Chuang Gan, Daniela Rus, Xavier Alameda-Pineda

Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN).

Ranked #11 on Multi-Object Tracking on MOT20 (using extra training data)

Image Classification Multi-Object Tracking +4

Feedback from Pixels: Output Regulation via Learning-Based Scene View Synthesis

1 code implementation19 Mar 2021 Murad Abu-Khalaf, Sertac Karaman, Daniela Rus

We propose a novel controller synthesis involving feedback from pixels, whereby the measurement is a high dimensional signal representing a pixelated image with Red-Green-Blue (RGB) values.

object-detection Object Detection

Adversarial Training is Not Ready for Robot Learning

no code implementations15 Mar 2021 Mathias Lechner, Ramin Hasani, Radu Grosu, Daniela Rus, Thomas A. Henzinger

Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop.

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

1 code implementation8 Mar 2021 Axel Brunnbauer, Luigi Berducci, Andreas Brandstätter, Mathias Lechner, Ramin Hasani, Daniela Rus, Radu Grosu

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms.

Continuous Control Reinforcement Learning (RL)

Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy

1 code implementation4 Mar 2021 Lucas Liebenwein, Cenk Baykal, Brandon Carter, David Gifford, Daniela Rus

Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks.

Network Pruning

Robust Place Recognition using an Imaging Lidar

1 code implementation3 Mar 2021 Tixiao Shan, Brendan Englot, Fabio Duarte, Carlo Ratti, Daniela Rus

We propose a methodology for robust, real-time place recognition using an imaging lidar, which yields image-quality high-resolution 3D point clouds.

Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space

1 code implementation19 Feb 2021 Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Lucas Liebenwein, Ryan Sander, Sertac Karaman, Daniela Rus

We demonstrate the effectiveness of our algorithm in learning competitive behaviors on a novel multi-agent racing benchmark that requires planning from image observations.

Reinforcement Learning (RL)

DiffPD: Differentiable Projective Dynamics

no code implementations15 Jan 2021 Tao Du, Kui Wu, Pingchuan Ma, Sebastien Wah, Andrew Spielberg, Daniela Rus, Wojciech Matusik

Inspired by Projective Dynamics (PD), we present Differentiable Projective Dynamics (DiffPD), an efficient differentiable soft-body simulator based on PD with implicit time integration.

Friction

Deep Learning Meets Projective Clustering

no code implementations ICLR 2021 Alaa Maalouf, Harry Lang, Daniela Rus, Dan Feldman

Based on this approach, we provide a novel architecture that replaces the original embedding layer by a set of $k$ small layers that operate in parallel and are then recombined with a single fully-connected layer.

Clustering

Aggregating Long-Term Context for Learning Laparoscopic and Robot-Assisted Surgical Workflows

no code implementations1 Sep 2020 Yutong Ban, Guy Rosman, Thomas Ward, Daniel Hashimoto, Taisei Kondo, Hidekazu Iwaki, Ozanan Meireles, Daniela Rus

With the understanding of the complete surgical workflow, the robots are able to assist the surgeons in intra-operative events, such as by giving a warning when the surgeon is entering specific keys or high-risk phases.

Surgical phase recognition

LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping

1 code implementation IEEE/RSJ International Conference on Intelligent Robots and Systems 2020 Tixiao Shan, Brendan Englot, Drew Meyers, Wei Wang, Carlo Ratti, Daniela Rus

We propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building.

Robotics

Deep Orientation Uncertainty Learning based on a Bingham Loss

1 code implementation ICLR 2020 Igor Gilitschenski, Roshni Sahoo, Wilko Schwarting, Alexander Amini, Sertac Karaman, Daniela Rus

Reasoning about uncertain orientations is one of the core problems in many perception tasks such as object pose estimation or motion estimation.

Motion Estimation Pose Estimation

On Coresets for Support Vector Machines

no code implementations15 Feb 2020 Murad Tukan, Cenk Baykal, Dan Feldman, Daniela Rus

A coreset is a small, representative subset of the original data points such that a models trained on the coreset are provably competitive with those trained on the original data set.

Small Data Image Classification

Provable Filter Pruning for Efficient Neural Networks

2 code implementations ICLR 2020 Lucas Liebenwein, Cenk Baykal, Harry Lang, Dan Feldman, Daniela Rus

We present a provable, sampling-based approach for generating compact Convolutional Neural Networks (CNNs) by identifying and removing redundant filters from an over-parameterized network.

SiPPing Neural Networks: Sensitivity-informed Provable Pruning of Neural Networks

2 code implementations11 Oct 2019 Cenk Baykal, Lucas Liebenwein, Igor Gilitschenski, Dan Feldman, Daniela Rus

We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy.

Deep Evidential Regression

4 code implementations NeurIPS 2020 Alexander Amini, Wilko Schwarting, Ava Soleimany, Daniela Rus

We demonstrate learning well-calibrated measures of uncertainty on various benchmarks, scaling to complex computer vision tasks, as well as robustness to adversarial and OOD test samples.

regression

D3PG: Deep Differentiable Deterministic Policy Gradients

no code implementations25 Sep 2019 Tao Du, Yunfei Li, Jie Xu, Andrew Spielberg, Kui Wu, Daniela Rus, Wojciech Matusik

Over the last decade, two competing control strategies have emerged for solving complex control tasks with high efficacy.

Model Predictive Control

Deep Evidential Uncertainty

no code implementations25 Sep 2019 Alexander Amini, Wilko Schwarting, Ava Soleimany, Daniela Rus

In this paper, we propose a novel method for training deterministic NNs to not only estimate the desired target but also the associated evidence in support of that target.

regression

Variational End-to-End Navigation and Localization

no code implementations25 Nov 2018 Alexander Amini, Guy Rosman, Sertac Karaman, Daniela Rus

We define a novel variational network capable of learning from raw camera data of the environment as well as higher level roadmaps to predict (1) a full probability distribution over the possible control commands; and (2) a deterministic control command capable of navigating on the route specified within the map.

Liquid Time-constant Recurrent Neural Networks as Universal Approximators

no code implementations1 Nov 2018 Ramin M. Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu

In this paper, we introduce the notion of liquid time-constant (LTC) recurrent neural networks (RNN)s, a subclass of continuous-time RNNs, with varying neuronal time-constant realized by their nonlinear synaptic transmission model.

ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics

no code implementations2 Oct 2018 Yuanming Hu, Jian-Cheng Liu, Andrew Spielberg, Joshua B. Tenenbaum, William T. Freeman, Jiajun Wu, Daniela Rus, Wojciech Matusik

The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and therefore they are significantly more computationally expensive to simulate.

Motion Planning

Can a Compact Neuronal Circuit Policy be Re-purposed to Learn Simple Robotic Control?

1 code implementation11 Sep 2018 Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu

Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as the model of biological neural circuits reparameterized for the control of an alternative task.

Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks

no code implementations11 Sep 2018 Ramin M. Hasani, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, Daniela Rus

In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level.

Spatial Uncertainty Sampling for End-to-End Control

no code implementations13 May 2018 Alexander Amini, Ava Soleimany, Sertac Karaman, Daniela Rus

Dropout training in deep NNs approximates Bayesian inference in a deep Gaussian process and can thus be used to estimate model uncertainty.

Autonomous Vehicles Bayesian Inference

Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds

no code implementations ICLR 2019 Cenk Baykal, Lucas Liebenwein, Igor Gilitschenski, Dan Feldman, Daniela Rus

We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output.

Generalization Bounds Neural Network Compression

Small Coresets to Represent Large Training Data for Support Vector Machines

no code implementations ICLR 2018 Cenk Baykal, Murad Tukan, Dan Feldman, Daniela Rus

Support Vector Machines (SVMs) are one of the most popular algorithms for classification and regression analysis.

A Nonparametric Model for Multimodal Collaborative Activities Summarization

no code implementations4 Sep 2017 Guy Rosman, John W. Fisher III, Daniela Rus

We demonstrate the utility of this model for inference tasks such as activity detection, classification, and summarization.

Action Detection Activity Detection

Coresets for Vector Summarization with Applications to Network Graphs

no code implementations ICML 2017 Dan Feldman, Sedat Ozer, Daniela Rus

We provide a deterministic data summarization algorithm that approximates the mean $\bar{p}=\frac{1}{n}\sum_{p\in P} p$ of a set $P$ of $n$ vectors in $\REAL^d$, by a weighted mean $\tilde{p}$ of a \emph{subset} of $O(1/\eps)$ vectors, i. e., independent of both $n$ and $d$.

Data Summarization

Baxter's Homunculus: Virtual Reality Spaces for Teleoperation in Manufacturing

no code implementations3 Mar 2017 Jeffrey I Lipton, Aidan J Fay, Daniela Rus

The control room is mapped to a space inside the robot to provide a sense of co-location within the robot.

Robotics

Dimensionality Reduction of Massive Sparse Datasets Using Coresets

no code implementations NeurIPS 2016 Dan Feldman, Mikhail Volkov, Daniela Rus

An open practical problem has been to compute a non-trivial approximation to the PCA of very large but sparse databases such as the Wikipedia document-term matrix in a reasonable time.

Dimensionality Reduction

Information-Driven Adaptive Structured-Light Scanners

no code implementations CVPR 2016 Guy Rosman, Daniela Rus, John W. Fisher III

We then demonstrate how different choices of relevant variable sets (corresponding to the subproblems of locatization and mapping) lead to different criteria for pattern selection and can be computed in an online fashion.

Pose Estimation

Coresets for k-Segmentation of Streaming Data

no code implementations NeurIPS 2014 Guy Rosman, Mikhail Volkov, Dan Feldman, John W. Fisher III, Daniela Rus

We consider the problem of computing optimal segmentation of such signals by k-piecewise linear function, using only one pass over the data by maintaining a coreset for the signal.

Segmentation Time Series +1

Cannot find the paper you are looking for? You can Submit a new open access paper.