Related papers: TRGP: Trust Region Gradient Projection for Continu…
Catastrophic forgetting in continual learning is a common destructive phenomenon in gradient-based neural networks that learn sequential tasks, and it is much different from forgetting in humans, who can learn and accumulate knowledge…
Recent studies on catastrophic forgetting during sequential learning typically focus on fixing the accuracy of the predictions for a previously learned task. In this paper we argue that the outputs of neural networks are subject to rapid…
Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate…
There is a recent proliferation of research on the integration of machine learning and optimization. One expansive area within this research stream is predictive-model embedded optimization, which proposes the use of pre-trained predictive…
Task-oriented grasping (TOG) refers to the problem of predicting grasps on an object that enable subsequent manipulation tasks. To model the complex relationships between objects, tasks, and grasps, existing methods incorporate semantic…
Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a…
While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high…
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus on training neural networks efficiently from a stream of…
Deep Reinforcement Learning agents often suffer from catastrophic forgetting, forgetting previously found solutions in parts of the input space when training on new data. Replay Memories are a common solution to the problem, decorrelating…
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning…
We consider trust-region methods for solving optimization problems where the objective is the sum of a smooth, nonconvex function and a nonsmooth, convex regularizer. We extend the global convergence theory of such methods to include…
Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting problem is a major problem in machine learning. Numerous continual…
The ability to continuously process and retain new information like we do naturally as humans is a feat that is highly sought after when training neural networks. Unfortunately, the traditional optimization algorithms often require large…
Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers…
We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to…
In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…
Backpropagation provides a generalized configuration for overcoming catastrophic forgetting. Optimizers such as SGD and Adam are commonly used for weight updates in continual learning and continual pre-training. However, access to gradient…
The deployment of quantized neural networks on edge devices, combined with privacy regulations like GDPR, creates an urgent need for machine unlearning in quantized models. However, existing methods face critical challenges: they induce…
Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…
In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training a new model and validating the model. This continual model…