Related papers: Learning Random Numbers to Realize Appendable Memo…

A critical component to enabling intelligent reasoning in partially observable environments is memory. Despite this importance, Deep Reinforcement Learning (DRL) agents have so far used relatively simple memory architectures, with the main…

Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may not be life-long legitimate due to privacy or copyright reasons. In practical scenarios,…

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly…

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…

Episodic memory is a psychology term which refers to the ability to recall specific events from the past. We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered…

Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning." Traditional gradient-based networks require a lot of data to learn, often through…

Meta-learning consists in learning learning algorithms. We use a Long Short Term Memory (LSTM) based network to learn to compute on-line updates of the parameters of another neural network. These parameters are stored in the cell state of…

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and…

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…

Neural networks suffer from catastrophic forgetting and are unable to sequentially learn new tasks without guaranteed stationarity in data distribution. Continual learning could be achieved via replay -- by concurrently training externally…

The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance…

Regardless of the marked differences between biological and artificial neural systems, one fundamental similarity is that they are essentially dynamical systems that can learn to imitate other dynamical systems, without knowing their…

Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Recent results in adaptive matter revived the interest in the implementation of novel devices able to perform brain-like operations. Here we introduce a training algorithm for a memristor network which is inspired in previous work on…

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…

An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its…

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…