Related papers: Artificial Learning in Artificial Memories

Artificial Intelligence has historically relied on planning, heuristics, and handcrafted approaches designed by experts. All the while claiming to pursue the creation of Intelligence. This approach fails to acknowledge that intelligence…

We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework…

In continual learning, a system learns from non-stationary data streams or batches without catastrophic forgetting. While this problem has been heavily studied in supervised image classification and reinforcement learning, continual…

Differentiable neural computers extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks such as graph traversal. However, such models are difficult to…

Learned optimizers are algorithms that can themselves be trained to solve optimization problems. In contrast to baseline optimizers (such as momentum or Adam) that use simple update rules derived from theoretical principles, learned…

Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory…

Deep learning based on artificial neural networks is a powerful machine learning method that, in the last few years, has been successfully used to realize tasks, e.g., image classification, speech recognition, translation of languages,…

Artificial intelligence (AI) tools such as large language models (LLMs) are already altering student learning. Unlike previous technologies, LLMs can independently solve problems regardless of student understanding, yet are not always…

In this study, we developed a learning method for constructing a neural network system capable of memorizing data and recalling it without parameter updates. The system we built using this method is called the Appendable Memory system. The…

Plans for a new type of artificial brain are possible because of realistic neurons in logically structured arrays of controlled toggles, one toggle per neuron. Controlled toggles can be made to compute, in parallel, parameters of critical…

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity…

In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in…

Artificial neural networks (ANNs) have emerged as an essential tool in machine learning, achieving remarkable success across diverse domains, including image and speech generation, game playing, and robotics. However, there exist…

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…

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,…

Artificial Intelligence (AI) is about making computers that do the sorts of things that minds can do, and as we progress towards this goal, we tend to increasingly delegate human tasks to machines. However, AI systems usually do these tasks…

Today, intelligent systems that offer artificial intelligence capabilities often rely on machine learning. Machine learning describes the capacity of systems to learn from problem-specific training data to automate the process of analytical…

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by…

In this work, a neural network is trained to replicate the code that trains it using only its own output as input. A paradigm for evolutionary self-replication in neural programs is introduced, where program parameters are mutated, and the…

The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limitation, agentic systems commonly incorporate memory modules…