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.
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
no code implementations • 5 Apr 2024 • Tim Seyde, Peter Werner, Wilko Schwarting, Markus Wulfmeier, Daniela Rus
Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks.
no code implementations • 2 Apr 2024 • Anass Bairouk, Mirjana Maras, Simon Herlin, Alexander Amini, Marc Blanchon, Ramin Hasani, Patrick Chareyre, Daniela Rus
Autonomous driving presents a complex challenge, which is usually addressed with artificial intelligence models that are end-to-end or modular in nature.
no code implementations • 2 Apr 2024 • Yao Du, Carlos M. Mateo, Mirjana Maras, Tsun-Hsuan Wang, Marc Blanchon, Alexander Amini, Daniela Rus, Omar Tahri
Unlike a traditional gyroscope, a visual gyroscope estimates camera rotation through images.
no code implementations • 3 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.
no code implementations • 25 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.
no code implementations • 18 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.
no code implementations • 26 Nov 2023 • Qi Yang, Shreya Ravikumar, Fynn Schmitt-Ulms, Satvik Lolla, Ege Demir, Iaroslav Elistratov, Alex Lavaee, Sadhana Lolla, Elaheh Ahmadi, Daniela Rus, Alexander Amini, Alejandro Perez
We present an automatic large language model (LLM) conversion approach that produces uncertainty-aware LLMs capable of estimating uncertainty with every prediction.
no code implementations • 21 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.
no code implementations • 26 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.
no code implementations • 5 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.
no code implementations • 6 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.
1 code implementation • 10 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.
no code implementations • 1 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.
no code implementations • 5 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.
no code implementations • 31 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.
no code implementations • 23 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?
1 code implementation • 19 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.
no code implementations • 23 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.
no code implementations • 5 Apr 2023 • Tsun-Hsuan Wang, Wei Xiao, Makram Chahine, Alexander Amini, Ramin Hasani, Daniela Rus
Modern end-to-end learning systems can learn to explicitly infer control from perception.
no code implementations • 21 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.
no code implementations • 16 Mar 2023 • Tsun-Hsuan Wang, Pingchuan Ma, Andrew Everett Spielberg, Zhou Xian, Hao Zhang, Joshua B. Tenenbaum, Daniela Rus, Chuang Gan
Existing work has typically been tailored for particular environments or representations.
1 code implementation • 9 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.
1 code implementation • 28 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.
2 code implementations • 13 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.
1 code implementation • 2 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.
no code implementations • 21 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.
1 code implementation • 29 Nov 2022 • Mathias Lechner, Đorđe Žikelić, Krishnendu Chatterjee, Thomas A. Henzinger, Daniela Rus
We study the problem of training and certifying adversarially robust quantized neural networks (QNNs).
1 code implementation • 22 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.
2 code implementations • 21 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.
1 code implementation • 21 Oct 2022 • Noel Loo, Ramin Hasani, Alexander Amini, Daniela Rus
In this limit, the kernel is frozen, and the underlying feature map is fixed.
no code implementations • 20 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.
no code implementations • 13 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.
no code implementations • 10 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.
2 code implementations • 10 Oct 2022 • Mathias Lechner, Ramin Hasani, Philipp Neubauer, Sophie Neubauer, Daniela Rus
Hyperparameter tuning is a fundamental aspect of machine learning research.
no code implementations • 9 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.
1 code implementation • 26 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.
Ranked #1 on SpO2 estimation on BIDMC
1 code implementation • 21 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.
no code implementations • 25 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.
no code implementations • 2 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.
1 code implementation • 26 May 2022 • Zhijian Liu, Haotian Tang, Alexander Amini, Xinyu Yang, Huizi Mao, Daniela Rus, Song Han
Multi-sensor fusion is essential for an accurate and reliable autonomous driving system.
Ranked #4 on 3D Object Detection on nuScenes
1 code implementation • 18 May 2022 • Ryan Sander, Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Sertac Karaman, Daniela Rus
Experience replay plays a crucial role in improving the sample efficiency of deep reinforcement learning agents.
no code implementations • 15 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.
no code implementations • 15 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.
no code implementations • 5 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.
no code implementations • 4 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.
no code implementations • 27 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.
no code implementations • 23 Nov 2021 • Tsun-Hsuan Wang, Alexander Amini, Wilko Schwarting, Igor Gilitschenski, Sertac Karaman, Daniela Rus
Data-driven simulators promise high data-efficiency for driving policy learning.
no code implementations • 23 Nov 2021 • Alexander Amini, Tsun-Hsuan Wang, Igor Gilitschenski, Wilko Schwarting, Zhijian Liu, Song Han, Sertac Karaman, Daniela Rus
Simulation has the potential to transform the development of robust algorithms for mobile agents deployed in safety-critical scenarios.
no code implementations • 22 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.
no code implementations • NeurIPS 2021 • Tim Seyde, Igor Gilitschenski, Wilko Schwarting, Bartolomeo Stellato, Martin Riedmiller, Markus Wulfmeier, Daniela Rus
Reinforcement learning (RL) for continuous control typically employs distributions whose support covers the entire action space.
no code implementations • 4 Oct 2021 • Cosimo Della Santina, Christian Duriez, Daniela Rus
Continuum soft robots are mechanical systems entirely made of continuously deformable elements.
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.
1 code implementation • 18 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.
1 code implementation • 25 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.
Ranked #36 on Sentiment Analysis on IMDb
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.
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.
1 code implementation • 13 Jun 2021 • Zahra Babaiee, Ramin Hasani, Mathias Lechner, Daniela Rus, Radu Grosu
Robustness to variations in lighting conditions is a key objective for any deep vision system.
no code implementations • 3 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.
no code implementations • 20 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.
no code implementations • 10 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.
no code implementations • 10 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.
no code implementations • 17 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.
no code implementations • 6 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).
2 code implementations • 28 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 #13 on Multi-Object Tracking on MOT20 (using extra training data)
1 code implementation • 19 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.
no code implementations • 15 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.
1 code implementation • 8 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.
1 code implementation • 4 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.
1 code implementation • 3 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.
no code implementations • 24 Feb 2021 • Brandon Araki, Xiao Li, Kiran Vodrahalli, Jonathan DeCastro, Micah J. Fry, Daniela Rus
Learning composable policies for environments with complex rules and tasks is a challenging problem.
Hierarchical Reinforcement Learning reinforcement-learning +1
1 code implementation • 19 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.
no code implementations • 15 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.
no code implementations • 27 Oct 2020 • Tim Seyde, Wilko Schwarting, Sertac Karaman, Daniela Rus
Learning complex robot behaviors through interaction requires structured exploration.
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.
no code implementations • 1 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.
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
4 code implementations • 8 Jun 2020 • Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus, Radu Grosu
We introduce a new class of time-continuous recurrent neural network models.
no code implementations • L4DC 2020 • Tim Seyde, Wilko Schwarting, Sertac Karaman, Daniela Rus
Deep exploration requires coordinated long-term planning.
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.
no code implementations • 15 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.
no code implementations • 14 Dec 2019 • Igor Gilitschenski, Guy Rosman, Arjun Gupta, Sertac Karaman, Daniela Rus
Our main contribution is the concept of learning context maps to improve the prediction task.
no code implementations • NeurIPS 2019 • Andrew Spielberg, Allan Zhao, Yuanming Hu, Tao Du, Wojciech Matusik, Daniela Rus
We validate the behavior of our algorithm with visualizations of the learned representation.
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.
2 code implementations • 11 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.
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.
no code implementations • 25 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.
no code implementations • 25 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.
no code implementations • 25 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.
no code implementations • 1 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.
no code implementations • 2 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.
no code implementations • 11 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.
1 code implementation • 11 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.
no code implementations • 13 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.
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.
no code implementations • 12 Feb 2018 • Xinxin Du, Marcelo H. Ang Jr., Sertac Karaman, Daniela Rus
Autonomous driving requires 3D perception of vehicles and other objects in the in environment.
Ranked #17 on 3D Object Detection on KITTI Cars Easy
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.
no code implementations • 4 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.
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 $d$.
no code implementations • 3 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
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.
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.
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.