Related papers: Anytime Learning - The next Step in Organic Comput…
In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorithms can improve performance on future tasks, their…
Machine learning has been successful in building control policies to drive a complex system to desired states in various applications (e.g. games, robotics, etc.). To be specific, a number of parameters of policy can be automatically…
We introduce the notion of a reproducible algorithm in the context of learning. A reproducible learning algorithm is resilient to variations in its samples -- with high probability, it returns the exact same output when run on two samples…
Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain…
The success of smart environments largely depends on their smartness of understanding the environments' ongoing situations. Accordingly, this task is an essence to smart environment central processors. Obtaining knowledge from the…
Living organisms process information to interact and adapt to their changing environment with the goal of finding food, mates or averting hazards. The structure of their niche has profound repercussions by both selecting their internal…
The developpment of the Internet of Things (IoT) concept revives Responsive Environments (RE) technologies. Nowadays, the idea of a permanent connection between physical and digital world is technologically possible. The capillar Internet…
Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned. This is…
The fields of neural computation and artificial neural networks have developed much in the last decades. Most of the works in these fields focus on implementing and/or learning discrete functions or behavior. However, technical, physical,…
Linear temporal logic (LTL) is a specification language for finite sequences (called traces) widely used in program verification, motion planning in robotics, process mining, and many other areas. We consider the problem of learning LTL…
Meta-learning, or "learning to learn," is a subfield of machine learning where the goal is to develop models and algorithms that can learn from various tasks and improve their learning process over time. Unlike traditional machine learning…
Drawing on the idea that brain development is a Darwinian process of ``evolution + selection'' and the idea that the current state is a local equilibrium state of many bodies with self-organization and evolution processes driven by the…
We propose a new anytime hierarchical clustering method that iteratively transforms an arbitrary initial hierarchy on the configuration of measurements along a sequence of trees we prove for a fixed data set must terminate in a chain of…
Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is assumed while relying only on a handful of examples to…
Can reproduction alone in the context of survival produce intelligence in our machines? In this work, self-replication is explored as a mechanism for the emergence of intelligent behavior in modern learning environments. By focusing purely…
Nature has found one method of organizing living matter, but maybe other options exist -- not yet discovered -- on how to create life. To study the life "as it could be" is the objective of an interdisciplinary field called Artificial Life…
Detecting and adapting to catastrophic failures in robotic systems requires a robot to learn its new dynamics quickly and safely to best accomplish its goals. To address this challenging problem, we propose probabilistically-safe, online…
Machine learning algorithms learn a desired input-output relation from examples in order to interpret new inputs. This is important for tasks such as image and speech recognition or strategy optimisation, with growing applications in the IT…
A robotic swarm that is required to operate for long periods in a potentially unknown environment can use both evolution and individual learning methods in order to adapt. However, the role played by the environment in influencing the…
A notion of time is fundamental in the study of dynamical systems. Time arises as a standalone dynamical system and also in solutions or trajectories as a special kind of map between systems. We characterize time by a universal property and…