Related papers: Mutual exclusivity as a challenge for deep neural …

Finding and facilitating commonalities between the linguistic behaviors of large language models and humans could lead to major breakthroughs in our understanding of the acquisition, processing, and evolution of language. However, most…

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence,…

Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distribution densely. We study a common setting where our task is not…

Humans can continuously learn new knowledge. However, machine learning models suffer from drastic dropping in performance on previous tasks after learning new tasks. Cognitive science points out that the competition of similar knowledge is…

Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that…

Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vector, matrix, or tensor in deep neural networks) to represent…

Various work has suggested that the memorability of an image is consistent across people, and thus can be treated as an intrinsic property of an image. Using computer vision models, we can make specific predictions about what people will…

Neural ordinary differential equations (Neural ODEs) propose the idea that a sequence of layers in a neural network is just a discretisation of an ODE, and thus can instead be directly modelled by a parameterised ODE. This idea has had…

The bias/variance tradeoff is fundamental to learning: increasing a model's complexity can improve its fit on training data, but potentially worsens performance on future samples. Remarkably, however, the human brain effortlessly handles a…

Neural networks are nowadays highly successful despite strong hardness results. The existing hardness results focus on the network architecture, and assume that the network's weights are arbitrary. A natural approach to settle the…

The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically…

Textual network embeddings aim to learn a low-dimensional representation for every node in the network so that both the structural and textual information from the networks can be well preserved in the representations. Traditionally, the…

Deep neural networks drive the success of natural language processing. A fundamental property of language is its compositional structure, allowing humans to systematically produce forms for new meanings. For humans, languages with more…

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…

Young children develop sophisticated internal models of the world based on their visual experience. Can such models be learned from a child's visual experience without strong inductive biases? To investigate this, we train state-of-the-art…

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop…

Understanding and controlling biasing effects in neural networks is crucial for ensuring accurate and fair model performance. In the context of classification problems, we provide a theoretical analysis demonstrating that the structure of a…

Often in language and other areas of cognition, whether two components of an object are identical or not determine whether it is well formed. We call such constraints identity effects. When developing a system to learn well-formedness from…

When acquiring syntax, children consistently choose hierarchical rules over competing non-hierarchical possibilities. Is this preference due to a learning bias for hierarchical structure, or due to more general biases that interact with…

Learning deep representations to solve complex machine learning tasks has become the prominent trend in the past few years. Indeed, Deep Neural Networks are now the golden standard in domains as various as computer vision, natural language…