Related papers: Learning beyond sensations: how dreams organize ne…

Decoding visual representations from brain signals has attracted significant attention in both neuroscience and artificial intelligence. However, the degree to which brain signals truly encode visual information remains unclear. Current…

There has been great progress in understanding of anatomical and functional microcircuitry of the primate cortex. However, the fundamental principles of cortical computation - the principles that allow the visual cortex to bind retinal…

Neural generative models can be used to learn complex probability distributions from data, to sample from them, and to produce probability density estimates. We propose a computational framework for developing neural generative models…

The mechanisms underlying major aspects of the human brain remain a mystery. It is unknown how verbal episodic memory is formed and integrated with sensory episodic memory. There is no consensus on the function and nature of dreaming. Here…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Active inference is a unifying theory for perception and action resting upon the idea that the brain maintains an internal model of the world by minimizing free energy. From a behavioral perspective, active inference agents can be seen as…

A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a…

Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human dreaming as a mechanism for internal simulation and knowledge restructuring, we introduce Dream2Learn (D2L), a…

Neuroscience has long informed the development of artificial neural networks, but the success of modern architectures invites, in turn, the converse: can modern networks teach us lessons about brain function? Here, we examine the structure…

Representation learning, i.e. the generation of representations useful for downstream applications, is a task of fundamental importance that underlies much of the success of deep neural networks (DNNs). Recently, robustness to adversarial…

A remarkable feature of human beings is their capacity for creative behaviour, referring to their ability to react to problems in ways that are novel, surprising, and useful. Transformational creativity is a form of creativity where the…

Humans and animals can learn new skills after practicing for a few hours, while current reinforcement learning algorithms require a large amount of data to achieve good performances. Recent model-based approaches show promising results by…

Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning. One characteristic of such experience is that the learner sees the same object…

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently…

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…

Massive data collection holds the promise of a better understanding of complex phenomena and, ultimately, better decisions. Representation learning has become a key driver of deep learning applications, as it allows learning latent spaces…

Transfer learning enhances the training of novel sensory and decision models by employing rich feature representations from large, pre-trained teacher models. Cognitive neuroscience shows that the human brain creates low-dimensional,…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…