Search Results for author:
Found 40 papers, 18 papers with code
The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits
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.
Optical Flow Matters: an Empirical Comparative Study on Fusing Monocular Extracted Modalities for Better Steering
This demonstrates the potential of optical flow data, combined with advanced neural network architectures (a CNN-based structure for fusing data and a Recurrence-based network for inferring a command from latent space), to enhance the performance of autonomous vehicles steering estimation.
Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inference
While our performance in steering angle estimation is comparable to existing methods, the integration of human-like perception through multi-task learning holds significant potential for advancing autonomous driving systems.
Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks
In this way, we obtain a full-stack imitation learning protocol that combines advances in 3D Gaussian splatting radiance field rendering, crafty programming of expert demonstration training data, and the task understanding capabilities of Liquid networks.
State-Free Inference of State-Space Models: The Transfer Function Approach
We approach designing a state-space model for deep learning applications through its dual representation, the transfer function, and uncover a highly efficient sequence parallel inference algorithm that is state-free: unlike other proposed algorithms, state-free inference does not incur any significant memory or computational cost with an increase in state size.
Exploring Latent Pathways: Enhancing the Interpretability of Autonomous Driving with a Variational Autoencoder
Autonomous driving presents a complex challenge, which is usually addressed with artificial intelligence models that are end-to-end or modular in nature.
Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?
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.
Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
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.
On the Size and Approximation Error of Distilled Sets
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?
Learning Stability Attention in Vision-based End-to-end Driving Policies
Modern end-to-end learning systems can learn to explicitly infer control from perception.
Infrastructure-based End-to-End Learning and Prevention of Driver Failure
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.
Dataset Distillation with Convexified Implicit Gradients
We propose a new dataset distillation algorithm using reparameterization and convexification of implicit gradients (RCIG), that substantially improves the state-of-the-art.
Ranked #1 on
Dataset Distillation - 1IPC
on TinyImageNet
Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
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.
Towards Cooperative Flight Control Using Visual-Attention
We propose an air-guardian system that facilitates cooperation between a pilot with eye tracking and a parallel end-to-end neural control system.
Evolution of Neural Tangent Kernels under Benign and Adversarial Training
In this limit, the kernel is frozen, and the underlying feature map is fixed.
Efficient Dataset Distillation Using Random Feature Approximation
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.
Pruning by Active Attention Manipulation
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
The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning.
PyHopper -- Hyperparameter optimization
Hyperparameter tuning is a fundamental aspect of machine learning research.
On the Forward Invariance of Neural ODEs
We propose a new method to ensure neural ordinary differential equations (ODEs) satisfy output specifications by using invariance set propagation.
Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap
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.
Liquid Structural State-Space Models
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
Entangled Residual Mappings
Residual mappings have been shown to perform representation learning in the first layers and iterative feature refinement in higher layers.
End-to-End Sensitivity-Based Filter Pruning
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.
Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving
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.
BarrierNet: A Safety-Guaranteed Layer for Neural Networks
This paper introduces differentiable higher-order control barrier functions (CBF) that are end-to-end trainable together with learning systems.
Interactive Analysis of CNN Robustness
While convolutional neural networks (CNNs) have found wide adoption as state-of-the-art models for image-related tasks, their predictions are often highly sensitive to small input perturbations, which the human vision is robust against.
Mixed-Memory RNNs for Learning Long-term Dependencies in Irregularly Sampled Time Series
These models, however, face difficulties when the input data possess long-term dependencies.
GoTube: Scalable Stochastic Verification of Continuous-Depth Models
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
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 #38 on
Sentiment Analysis
on IMDb
Sparse Flows: Pruning Continuous-depth Models
Our empirical results suggest that pruning improves generalization for neural ODEs in generative modeling.
Causal Navigation by Continuous-time Neural Networks
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.
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
Robustness to variations in lighting conditions is a key objective for any deep vision system.
Adversarial Training is Not Ready for Robot Learning
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
World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms.
On The Verification of Neural ODEs with Stochastic Guarantees
We show that Neural ODEs, an emerging class of time-continuous neural networks, can be verified by solving a set of global-optimization problems.
Neural circuit policies enabling auditable autonomy
A central goal of artificial intelligence in high-stakes decision-making applications is to design a single algorithm that simultaneously expresses generalizability by learning coherent representations of their world and interpretable explanations of its dynamics.
Learning Long-Term Dependencies in Irregularly-Sampled Time Series
These models, however, face difficulties when the input data possess long-term dependencies.
Ranked #10 on
Sequential Image Classification
on Sequential MNIST
Liquid Time-constant Networks
We introduce a new class of time-continuous recurrent neural network models.
Can a Compact Neuronal Circuit Policy be Re-purposed to Learn Simple Robotic Control?
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.
