Related papers: How Psychological Learning Paradigms Shaped and Co…

Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few examples, and combining these rules to form compositional rule-based…

Though modern neural networks have achieved impressive performance in both vision and language tasks, we know little about the functions that they implement. One possibility is that neural networks implicitly break down complex tasks into…

Humans excel at applying learned behavior to unlearned situations. A crucial component of this generalization behavior is our ability to compose/decompose a whole into reusable parts, an attribute known as compositionality. One of the…

Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failing when contexts shift or goals evolve. This paper argues…

Analogical reasoning lies at the core of human cognition and remains a fundamental challenge for artificial intelligence. Raven's Progressive Matrices (RPM) serve as a widely used benchmark to assess abstract reasoning by requiring the…

Ever since the creation of the first artificial intelligence (AI) machinery built on machine learning (ML), public society has entertained the idea that eventually computers could become sentient and develop a consciousness of their own. As…

As synthetic content increasingly infiltrates the web, generative AI models may be retrained on their own outputs: a process termed "autophagy". This leads to model collapse: a progressive loss of performance and diversity across…

Current AI alignment paradigms rely on behavioral correction: external supervisors (e.g., RLHF) observe outputs, judge against preferences, and adjust parameters. This paper argues that behavioral correction is structurally analogous to an…

The human cognitive system exhibits remarkable flexibility and generalization capabilities, partly due to its ability to form low-dimensional, compositional representations of the environment. In contrast, standard neural network…

Artificial intelligence (AI) research today is largely driven by ever-larger neural network models trained on graphics processing units (GPUs). This paradigm has yielded remarkable progress, but it also risks entrenching a hardware lottery…

In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess effective generalization abilities. It is…

Artificial Expert Intelligence (AEI) seeks to transcend the limitations of both Artificial General Intelligence (AGI) and narrow AI by integrating domain-specific expertise with critical, precise reasoning capabilities akin to those of top…

The AI-alignment problem arises when there is a discrepancy between the goals that a human designer specifies to an AI learner and a potential catastrophic outcome that does not reflect what the human designer really wants. We argue that a…

The study of complex adaptive systems, pioneered in physics, biology, and the social sciences, offers important lessons for AI governance. Contemporary AI systems and the environments in which they operate exhibit many of the properties…

In this paper we examine historical failures of artificial intelligence (AI) and propose a classification scheme for categorizing future failures. By doing so we hope that (a) the responses to future failures can be improved through…

Although AI has significant potential to transform society, there are serious concerns about its ability to behave and make decisions responsibly. Many ethical regulations, principles, and guidelines for responsible AI have been issued…

Making neural networks remember over the long term has been a longstanding issue. Although several external memory techniques have been introduced, most focus on retaining recent information in the short term. Regardless of its importance,…

AI-powered language learning tools increasingly provide instant, personalised feedback to millions of learners worldwide. However, this feedback can fail in ways that are difficult for learners--and even teachers--to detect, potentially…

Artificial neural networks used for reinforcement learning are structurally rigid, meaning that each optimized parameter of the network is tied to its specific placement in the network structure. It also means that a network only works with…

This paper offers a roadmap for the development of scalable aligned artificial intelligence (AI) from first principle descriptions of natural intelligence. In brief, a possible path toward scalable aligned AI rests upon enabling artificial…