431 citations · 844 across the 46 of their papers we have counts for
20 papers · 1 filter
Batch Model Consolidation: A Multi-Task Model Consolidation Framework
Iordanis Fostiropoulos, Jiaye Zhu, Laurent Itti
In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches…
Lightweight Learner for Shared Knowledge Lifelong Learning
Yunhao Ge, Yuecheng Li, Di Wu +12
In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicat…
Reproducibility Requires Consolidated Artifacts
Iordanis Fostiropoulos, Bowman Brown, Laurent Itti
Machine learning is facing a 'reproducibility crisis' where a significant number of works report failures when attempting to reproduce previously published results. We evaluate the…
Supervised Contrastive Prototype Learning: Augmentation Free Robust Neural Network
Iordanis Fostiropoulos, Laurent Itti
Transformations in the input space of Deep Neural Networks (DNN) lead to unintended changes in the feature space. Almost perceptually identical inputs, such as adversarial examples…
Invariant Structure Learning for Better Generalization and Causal Explainability
Yunhao Ge, Sercan Ö. Arik, Jinsung Yoon +3
Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Lear…
Model2Detector: Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps
Sumedh A Sontakke, Buvaneswari Ramanan, Laurent Itti +1
Out-of-distribution detection is an important capability that has long eluded vanilla neural networks. Deep Neural networks (DNNs) tend to generate over-confident predictions when…
GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL
Sumedh A Sontakke, Stephen Iota, Zizhao Hu +3
Out-of-distribution (OOD) detection is a well-studied topic in supervised learning. Extending the successes in supervised learning methods to the reinforcement learning (RL) settin…
Lifelong Learning Without a Task Oracle
Amanda Rios, Laurent Itti
Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned, termed "catastrophic forgetting". Many state-of-the-…
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Sumedh A. Sontakke, Arash Mehrjou, Laurent Itti +1
Animals exhibit an innate ability to learn regularities of the world through interaction. By performing experiments in their environment, they are able to discern the causal factor…
SHERLock: Self-Supervised Hierarchical Event Representation Learning
Sumegh Roychowdhury, Sumedh A. Sontakke, Nikaash Puri +5
Temporal event representations are an essential aspect of learning among humans. They allow for succinct encoding of the experiences we have through a variety of sensory inputs. Al…
Beneficial Perturbations Network for Defending Adversarial Examples
Shixian Wen, Amanda Rios, Laurent Itti
Deep neural networks can be fooled by adversarial attacks: adding carefully computed small adversarial perturbations to clean inputs can cause misclassification on state-of-the-art…
Attentive Feature Reuse for Multi Task Meta learning
Kiran Lekkala, Laurent Itti
We develop new algorithms for simultaneous learning of multiple tasks (e.g., image classification, depth estimation), and for adapting to unseen task/domain distributions within th…
Meta Adaptation using Importance Weighted Demonstrations
Kiran Lekkala, Sami Abu-El-Haija, Laurent Itti
Imitation learning has gained immense popularity because of its high sample-efficiency. However, in real-world scenarios, where the trajectory distribution of most of the tasks dyn…
Adversarial Training: embedding adversarial perturbations into the parameter space of a neural network to build a robust system
Shixian Wen, Laurent Itti
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there a…
Beneficial perturbation network for continual learning
Shixian Wen, Laurent Itti
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during l…
Learning Causal State Representations of Partially Observable Environments
Amy Zhang, Zachary C. Lipton, Luis Pineda +5
Intelligent agents can cope with sensory-rich environments by learning task-agnostic state abstractions. In this paper, we propose an algorithm to approximate causal states, which…
Closed-Loop Memory GAN for Continual Learning
Amanda Rios, Laurent Itti
Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic for…
Overcoming catastrophic forgetting problem by weight consolidation and long-term memory
Shixian Wen, Laurent Itti
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during l…
metricDTW: local distance metric learning in Dynamic Time Warping
Jiaping Zhao, Zerong Xi, Laurent Itti
We propose to learn multiple local Mahalanobis distance metrics to perform k-nearest neighbor (kNN) classification of temporal sequences. Temporal sequences are first aligned by dy…
Active Long Term Memory Networks
Tommaso Furlanello, Jiaping Zhao, Andrew M. Saxe +2
Continual Learning in artificial neural networks suffers from interference and forgetting when different tasks are learned sequentially. This paper introduces the Active Long Term…