To exploit, UCT often selects the same action on successive trials, which can result in it getting stuck in local optima.

Monte-Carlo Tree Search (MCTS) methods, such as Upper Confidence Bound applied to Trees (UCT), are instrumental to automated planning techniques.

Monte-Carlo Tree Search (MCTS) methods, such as Upper Confidence Bound applied to Trees (UCT), are instrumental to automated planning techniques. However, UCT can be slow to explore an optimal action when it initially appears inferior to other actions. Maximum ENtropy Tree-Search (MENTS) incorporates the maximum entropy principle into an MCTS approach, utilising Boltzmann policies to sample actions, naturally encouraging more exploration. In this paper, we highlight a major limitation of MENTS: optimal actions for the maximum entropy objective do not necessarily correspond to optimal actions for the original objective. We introduce two algorithms, Boltzmann Tree Search (BTS) and Decaying ENtropy Tree-Search (DENTS), that address these limitations and preserve the benefits of Boltzmann policies, such as allowing actions to be sampled faster by using the Alias method. Our empirical analysis shows that our algorithms show consistent high performance across several benchmark domains, including the game of Go.

Dents on the aircraft skin are frequent and may easily go undetected during airworthiness checks, as their inspection process is tedious and extremely subject to human factors and environmental conditions. Nowadays, 3D scanning technologies are being proposed for more reliable, human-independent measurements, yet the process of inspection and reporting remains laborious and time consuming because data acquisition and validation are still carried out by the engineer. For full automation of dent inspection, the acquired point cloud data must be analysed via a reliable segmentation algorithm, releasing humans from the search and evaluation of damage. This paper reports on two developments towards automated dent inspection. The first is a method to generate a synthetic dataset of dented surfaces to train a fully convolutional neural network. The training of machine learning algorithms needs a substantial volume of dent data, which is not readily available. Dents are thus simulated in random positions and shapes, within criteria and definitions of a Boeing 737 structural repair manual. The noise distribution from the scanning apparatus is then added to reflect the complete process of 3D point acquisition on the training. The second proposition is a surface fitting strategy to convert 3D point clouds to 2.5D. This allows higher resolution point clouds to be processed with a small amount of memory compared with state-of-the-art methods involving 3D sampling approaches. Simulations with available ground truth data show that the proposed technique reaches an intersection-over-union of over 80%. Experiments over dent samples prove an effective detection of dents with a speed of over 500 000 points per second.

It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures. Existing methods mainly resolve this issue by retraining the entire model to impose the uncertainty quantification capability so that the learned model can achieve desired performance in accuracy and uncertainty prediction simultaneously. However, training the model from scratch is computationally expensive and may not be feasible in many situations. In this work, we consider a more practical post-hoc uncertainty learning setting, where a well-trained base model is given, and we focus on the uncertainty quantification task at the second stage of training. We propose a novel Bayesian meta-model to augment pre-trained models with better uncertainty quantification abilities, which is effective and computationally efficient. Our proposed method requires no additional training data and is flexible enough to quantify different uncertainties and easily adapt to different application settings, including out-of-domain data detection, misclassification detection, and trustworthy transfer learning. We demonstrate our proposed meta-model approach's flexibility and superior empirical performance on these applications over multiple representative image classification benchmarks.

This article first appeared in IndustryWeek. As manufacturers begin to integrate AI solutions into production lines, data scarcity has emerged as a major challenge. Unlike consumer Internet companies, which have data from billions of users to train powerful AI models, collecting massive training sets in manufacturing is often not feasible. For example, in automotive manufacturing, where lean Six Sigma practices have been widely adopted, most OEMs and Tier One suppliers strive to have fewer than three to four defects per million parts. The rarity of these defects makes it challenging to have sufficient defect data to train visual inspection models. In a recent MAPI survey, 58% of research respondents reported that the most significant barrier to deployment of AI solutions pertained to a lack of data resources.

Neil Lawrence had an interesting observation about the current state of machine learning, and linked it to fast ball games: "[…] the dynamics of the game will evolve. In the long run, the right way of playing football is to position yourself intelligently and to wait for the ball to come to you. You'll need to run up and down a bit, either to respond to how the play is evolving or to get out of the way of the scrum when it looks like it might flatten you." Neil Lawrence is known for his work in Gaussian Processes and is a proponent of data efficiency. He used to be professor at University of Sheffield, is now with Amazon. The ball has come to him.

As a former women's health medical practitioner, Dr. Michael Dent is at his core a physician on a mission to save lives. But rather than treating patients individually, he's out to save them on a global scale. That was his goal when he founded Fort Myers-based NeoGenomics in 2002: helping to grow the cancer diagnostics lab company from a $300,000 capital investment into publicly held company with $277 million in revenue in 2018. He says his newest venture, Bonita Springs-based HealthLynked, has even greater potential. HealthLynked is first and foremost a technology company with an emphasis on health care by linking patients with providers on multiple levels through a cloud-based software platform, Dent, 55, says.

So far, the impact of information technology on overall productivity has been a mixed bag, and even disappointing. IT has been reshaping workplaces in a big way since the 1980s, yet, there appears to be little to show for all this progress -- many argue that technology may even inhibit productivity growth. There are many reasons why the proliferation of technology doesn't automatically translate to productivity growth. For one, "technological disruption is, well, disruptive," Harvard's Jeffrey Frankel observed in a recent World Economic Forum report. "It demands that people learn new skills, adapt to new systems, and change their behavior. While a new iteration of computer software or hardware may offer more capacity, efficiency, or performance, those advantages are at least partly offset by the time users have to spend learning to use it. And glitches often bedevil the transition."

So far, the impact of information technology on overall productivity has been a mixed bag, and even disappointing.