My Google Schoolar Profile Page

In vitro neurons learn and exhibit sentience when embodied in a simulated game-world

Integrating neurons into digital systems to leverage their innate intelligence may enable performance infeasible with silicon alone, along with providing insight into the cellular origin of intelligence. We developed DishBrain, a system which exhibits natural intelligence by harnessing the inherent adaptive computation of neurons in a structured environment. In vitro neural networks from human or rodent origins, are integrated with in silico computing via high-density multielectrode array. Through electrophysiological stimulation and recording, cultures were embedded in a simulated game-world, mimicking the arcade game 'Pong'. Applying a previously untestable theory of active inference via the Free Energy Principle, we found that learning was apparent within five minutes of real-time gameplay, not observed in control conditions. Further experiments demonstrate the importance of closed-loop structured feedback in eliciting learning over time. Cultures display the ability to self-organise in a goal-directed manner in response to sparse sensory information about the consequences of their actions.

Open access from Publisher

Machine learning approaches for imaging-based prognostication of the outcome of surgery for mesial temporal lobe epilepsy

Around 30% of patients undergoing surgical resection for drug-resistant mesial temporal lobe epilepsy (MTLE) do not obtain seizure freedom. Success of anterior temporal lobe resection (ATLR) critically depends on the careful selection of surgical candidates, aiming at optimizing seizure freedom while minimizing postoperative morbidity. Structural MRI and FDG-PET neuroimaging are routinely used in presurgical assessment and guide the decision to proceed to surgery. In this study, we evaluate the potential of machine learning techniques applied to standard presurgical MRI and PET imaging features to provide enhanced prognostic value relative to current practice.

Open access from Publisher

ExIt-OOS: Towards Learning from Planning in Imperfect Information Games

Presented at the NeurIPS 2018 Deep Reinforcement Learning Workshop in Montreal

The current state of the art in playing many important perfectinformation games, including Chess and Go, combines planning anddeep reinforcement learning with self-play. We extend this approach to imperfect information games and present ExIt-OOS, a novel approach to playing imperfect information games within the Expert Iteration framework and inspired by AlphaZero. We use Online Outcome Sampling, an online search algorithm for imperfect information games in place of MCTS. While training online, our neural strategy is used to improve the accuracy of playouts in OOS, allowing a learning and planning feedback loop for imperfect information games.

arXiv | PDF | GitHub | Papers with Code

Generative Visual Rationales

Interpretability and small labelled datasets are key issues in the practical application of deep learning, particularly in areas such as medicine. In this paper, we present a semi-supervised technique that addresses both these issues by leveraging large unlabelled datasets to encode and decode images into a dense latent representation. Using chest radiography as an example, we apply this encoder to other labelled datasets and apply simple models to the latent vectors to learn algorithms to identify heart failure.

arXiv | PDF

Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis

Generative Adversarial Neural Networks (GANs) are applied to the synthetic generation of prostate lesion MRI images. GANs have been applied to a variety of natural images, is shown show that the same techniques can be used in the medical domain to create realistic looking synthetic lesion images. 16mm x 16mm patches are extracted from 330 MRI scans from the SPIE ProstateX Challenge 2016 and used to train a Deep Convolutional Generative Adversarial Neural Network (DCGAN) utilizing cutting edge techniques. Synthetic outputs are compared to real images and the implicit latent representations induced by the GAN are explored. Training techniques and successful neural network architectures are explained in detail.

arXiv | PDF

Support vector machines for prostate lesion classification

Support vector machines (SVM) are applied to the problem of prostate lesion classification for the SPIE ProstateX Challenge 2016, achieving a score of 0.82 AUC on held-out test data. Square 5mm transverse image patches are extracted around each lesion center from aligned MRI scans. Three MRI modalities are simultaneously analyzed: T2-weighted, apparent diffusion coefficient (ADC) and volume transfer constant (Ktrans). Extracted patches are used to train a binary classifier to predict clinical significance. The machine learning algorithm is trained on 76 positive cases and 254 negative cases (330 total) from the challenge. The method is conceptually simple, trains in a few seconds and yields competitive results.

SPIE Digital Library | PDF

Detection of prostate cancer on multiparametric MRI

In this manuscript, we describe our approach and methods to the ProstateX challenge, which achieved an overall AUC of 0.84 and the runner-up position. We train a deep convolutional neural network to classify lesions marked on multiparametric MRI of the prostate as clinically significant or not. We implement a novel addition to the standard convolutional architecture described as auto-windowing which is clinically inspired and designed to overcome some of the difficulties faced in MRI interpretation, where high dynamic ranges and low contrast edges may cause difficulty for traditional convolutional neural networks trained on high contrast natural imagery. We demonstrate that this system can be trained end to end and outperforms a similar architecture without such additions. Although a relatively small training set was provided, we use extensive data augmentation to prevent overfitting and transfer learning to improve convergence speed, showing that deep convolutional neural networks can be feasibly trained on small datasets.

SPIE Digital Library