Both Minsky's" society of mind" and Schmidhuber's" learning to think" inspire diverse
societies of large multimodal neural networks (NNs) that solve problems by interviewing …

Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic
information about good policies can be extracted from offline data which lack explicit …

In this paper, hypernetworks are trained to generate behaviors across a range of unseen
task conditions, via a novel TD-based training objective and data from a set of near-optimal …

Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The
program of an RNN is its weight matrix. How to learn useful representations of RNN weights …

There are two important things in science:(A) Finding answers to given questions, and (B)
Coming up with good questions. Our artificial scientists not only learn to answer given …

Retail banks use Asset Liability Management (ALM) to hedge interest rate risk associated
with differences in maturity and predictability of their loan and deposit portfolios. The …

Reinforcement Learning (RL) is a subfield of Artificial Intelligence that studies how machines
can make decisions by learning from their interactions with an environment. The key aspect …

Abstract Retail banks use Asset Liability Management (ALM) to hedge interest rate risk
associated with differences in maturity and predictability of their loan and deposit portfolios …

Deep reinforcement learning (RL) is a recent approach to sequential decision making
problems whereby agents parametrised by deep neural networks are trained by trial and …

While highly successful in many different domains, most artificial neural networks suffer from
a severe limitation; they use the same parameters for different inputs. Different examples can …