Related papers: BinPlay: A Binary Latent Autoencoder for Generativ…

Artificial neural networks (ANNs) continue to face challenges in continual learning, particularly due to catastrophic forgetting, the loss of previously learned knowledge when acquiring new tasks. Inspired by memory consolidation in the…

The knowledge replay technique has been widely used in many tasks such as continual learning and continuous domain adaptation. The key lies in how to effectively encode the knowledge extracted from previous data and replay them during…

Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where complex models are incrementally trained on small batches of…

On-device learning remains a formidable challenge, especially when dealing with resource-constrained devices that have limited computational capabilities. This challenge is primarily rooted in two key issues: first, the memory available on…

In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained with additional…

Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the…

A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural…

In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such…

Continual Learning entails progressively acquiring knowledge from new data while retaining previously acquired knowledge, thereby mitigating ``Catastrophic Forgetting'' in neural networks. Our work presents a novel uncertainty-driven…

Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by…

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

Replay is a powerful strategy to promote learning in artificial intelligence and the brain. However, the conditions to generate it and its functional advantages have not been fully recognized. In this study, we develop a modular…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

A recent trend in binary code analysis promotes the use of neural solutions based on instruction embedding models. An instruction embedding model is a neural network that transforms sequences of assembly instructions into embedding vectors.…

Continual learning seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the catastrophic forgetting of previous tasks. One effective solution is replay, which involves storing few previous…

Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of…

Modern Neural Machine Translation systems exhibit strong performance in several different languages and are constantly improving. Their ability to learn continuously is, however, still severely limited by the catastrophic forgetting issue.…

Artificial learning systems aspire to mimic human intelligence by continually learning from a stream of tasks without forgetting past knowledge. One way to enable such learning is to store past experiences in the form of input examples in…