Related papers: A new model for Cerebellar computation
We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for…
Continual learning is the ability to acquire new knowledge without forgetting the previously learned one, assuming no further access to past training data. Neural network approximators trained with gradient descent are known to fail in this…
The ability to quickly learn new knowledge (e.g. new classes or data distributions) is a big step towards human-level intelligence. In this paper, we consider scenarios that require learning new classes or data distributions quickly and…
Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…
Catastrophic forgetting - the tendency of neural networks to forget previously learned data when learning new information - remains a central challenge in continual learning. In this work, we adopt a behavioral approach, observing a…
A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model represented by a transition graph between sets of states, with transitions attributed with…
Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based…
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…
In continual learning, knowledge must be preserved and re-used between tasks, maintaining good transfer to future tasks and minimizing forgetting of previously learned ones. While several practical algorithms have been devised for this…
Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly,…
Motor control requires sensory feedback, and the nature of this feedback has implications for the tasks of the central nervous system (CNS): for an approximately linear mechanical system (e.g., a freely standing person, a rider on a…
Basic experimental findings about human working memory can be described by an algebra built on high-dimensional binary states, representing information items, and two operations: multiplication for binding and addition for bundling. In…
How to learn an effective reinforcement learning-based model for control tasks from high-level visual observations is a practical and challenging problem. A key to solving this problem is to learn low-dimensional state representations from…
World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are independent or sparsely dependent on action signals often exist,…
Even as machine learning exceeds human-level performance on many applications, the generality, robustness, and rapidity of the brain's learning capabilities remain unmatched. How cognition arises from neural activity is a central open…
This paper introduces the Contextual Evaluation Model (CEM), a novel method for knowledge representation and manipulation. The CEM differs from existing models in that it integrates facts, patterns and sequences into a single contextual…
A common view on the brain learning processes proposes that the three classic learning paradigms -- unsupervised, reinforcement, and supervised -- take place in respectively the cortex, the basal-ganglia, and the cerebellum. However,…
Timely and accurate diagnosis of neurodegenerative disorders, such as Alzheimer's disease, is central to disease management. Existing deep learning models require large-scale annotated datasets and often function as "black boxes".…
Learning shared structure across environments facilitates rapid learning and adaptive behavior in neural systems. This has been widely demonstrated and applied in machine learning to train models that are capable of generalizing to novel…
The infrequent occurrence of overfitting in deep neural networks is perplexing: contrary to theoretical expectations, increasing model size often enhances performance in practice. But what if overfitting does occur, though restricted to…