Search By Subject

There is now significant historical data available on decision making in organizations, consisting of the decision problem, what decisions were made, and how desirable the outcomes were. Using this data, it is possible to learn a surrogate model, and ...

The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most commonly-used in ...

Consumer-grade 3D printers have made the fabrication of aesthetic objects and static assemblies easier, opening the door to automate the design of such objects. However, while static designs are easily produced with 3D printing, functional designs, with ...

Deep neural networks (DNNs) have produced state-of-the-art results in many benchmarks and problem domains. However, the success of DNNs depends on the proper configuration of its architecture and hyperparameters. Such a configuration is difficult and as ...

Computational models are crucial in understanding brain function. Their architecture is designed to replicate known brain structures, and the behavior that emerges is then compared to observed fMRI and other imaging techniques. As the models become more ...

An important benefit of multi-objective search is that it maintains a diverse population of candidates, which helps in deceptive problems in particular. Not all diversity is useful, however: candidates that optimize only one objective while ignoring ...

A cyberphysical avatar is a semi-autonomous robot that adjusts to an unstructured environment and performs physical tasks subject to critical timing constraints while under human supervision. This article first realizes a cyberphysical avatar that ...

Consumer-grade printers are widely available, but their ability to print complex objects is limited. Therefore, new designs need to be discovered that serve the same function, but are printable. A representative such problem is to produce a working, ...

As a classic example of imperfect information games, Heads-Up No-limit Texas Holdem (HUNL) has been studied extensively in recent years. While state-of-the-art approaches based on Nash equilibrium have been successful, they lack the ability to model and ...

Multitask learning, i.e. learning several tasks at once with the same neural network, can improve performance in each of the tasks. Designing deep neural network architectures for multitask learning is a challenge: There are many ways to tie the tasks ...

Behavior domination is proposed as a tool for understanding and harnessing the power of evolutionary systems to discover and exploit useful stepping stones. Novelty search has shown promise in overcoming deception by collecting diverse stepping stones, ...

Conversion optimization means designing a web interface so that as many users as possible take a desired action on it, such as register or purchase. Such design is usually done by hand, testing one change at a time through A/B testing, or a limited ...

Capabilities of extrusion-based 3D-printers have progressed significantly, but complex forms are still challenging to print. One major problem is overhanging surfaces. These surfaces require extra support structure to be printed, wasting material and ...

Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful technique for solving challenging reinforcement learning problems. Compared to traditional (e.g. value-function based) methods, neuroevolution is especially ...

Reinforcement Learning agents with memory are constructed in this paper by extending neuroevolutionary algorithm NEAT to incorporate LSTM cells, i.e. special memory units with gating logic. Initial evaluation on POMDP tasks indicated that memory ...

Novelty search and related diversity-driven algorithms provide a promising approach to overcoming deception in complex domains. The behavior characterization (BC) is a critical choice in the application of such algorithms. The BC maps each evaluated ...

In an age-layered evolutionary algorithm, candidates are evaluated on a small number of samples first; if they seem promising, they are evaluated with more samples, up to the entire training set. In this manner, weak candidates can be eliminated quickly,...

Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful technique for solving challenging reinforcement learning problems. Compared to traditional (e.g. value-function based) methods, neuroevolution is especially ...

While evolutionary computation is well suited for automatic discovery in engineering, it can also be used to gain insight into how humans and organizations could perform more effectively in competitive problem-solving domains. This paper formalizes ...