Cell detection and cell type classification from biomedical images play an important role for high-throughput imaging and various clinical application. While classification of single cell sample can be performed with standard computer vision and machine learning methods, analysis of multi-label samples (region containing congregating cells) is more challenging, as separation of individual cells can be difficult (e.g. touching cells) or even impossible (e.g. overlapping cells). As multi-instance images are common in analyzing Red Blood Cell (RBC) for Sickle Cell Disease (SCD) diagnosis, we develop and implement a multi-instance cell detection and classification framework to address this challenge. The framework firstly trains a region proposal model based on Region-based Convolutional Network (RCNN) to obtain bounding-boxes of regions potentially containing single or multiple cells from input microscopic images, which are extracted as image patches. High-level image features are then calculated from image patches through a pre-trained Convolutional Neural Network (CNN) with ResNet-50 structure. Using these image features inputs, six networks are then trained to make multi-label prediction of whether a given patch contains cells belonging to a specific cell type. As the six networks are trained with image patches consisting of both individual cells and touching/overlapping cells, they can effectively recognize cell types that are presented in multi-instance image samples. Finally, for the purpose of SCD testing, we train another machine learning classifier to predict whether the given image patch contains abnormal cell type based on outputs from the six networks. Testing result of the proposed framework shows that it can achieve good performance in automatic cell detection and classification.

Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language by forming paragraphs from sentences and sentences from words, hierarchical models have usually not worked that much better than their traditional seq2seq counterparts. This effect is mainly because either the hierarchical attention mechanisms are too sparse using hard attention or noisy using soft attention. In this paper, we propose a method based on extracting the highlights of a document; a key concept that is conveyed in a few sentences. In a typical text summarization dataset consisting of documents that are 800 tokens in length (average), capturing long-term dependencies is very important, e.g., the last sentence can be grouped with the first sentence of a document to form a summary. LSTMs (Long Short-Term Memory) proved useful for machine translation. However, they often fail to capture long-term dependencies while modeling long sequences. To address these issues, we have adapted Neural Semantic Encoders (NSE) to text summarization, a class of memory-augmented neural networks by improving its functionalities and proposed a novel hierarchical NSE that outperforms similar previous models significantly. The quality of summarization was improved by augmenting linguistic factors, namely lemma, and Part-of-Speech (PoS) tags, to each word in the dataset for improved vocabulary coverage and generalization. The hierarchical NSE model on factored dataset outperformed the state-of-the-art by nearly 4 ROUGE points. We further designed and used the first GPU-based self-critical Reinforcement Learning model.

With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YOLO is generally considered as one of the faster object detectors for low-end devices and is the basis for our work. Our experiments on this network have shown that Tiny-YOLO can achieve 0.14 frames per second(FPS) on the Raspberry Pi 3 B, which is too slow for soccer playing autonomous humanoid robots detecting goal and ball objects. In this paper we propose an adaptation to the YOLO CNN model named xYOLO, that can achieve object detection at a speed of 9.66 FPS on the Raspberry Pi 3 B. This is achieved by trading an acceptable amount of accuracy, making the network approximately 70 times faster than Tiny-YOLO. Greater inference speed-ups were also achieved on a desktop CPU and GPU. Additionally we contribute an annotated Darknet dataset for goal and ball detection.

The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited theoretical understanding for this improvement. In this work, we analyze overparameterized deep residual networks trained by gradient descent following random initialization, and demonstrate that (i) the class of networks learned by gradient descent constitutes a small subset of the entire neural network function class, and (ii) this subclass of networks is sufficiently large to guarantee small training error. By showing (i) we are able to demonstrate that deep residual networks trained with gradient descent have a small generalization gap between training and test error, and together with (ii) this guarantees that the test error will be small. Our optimization and generalization guarantees require overparameterization that is only logarithmic in the depth of the network, while all known generalization bounds for deep non-residual networks have overparameterization requirements that are at least polynomial in the depth. This provides an explanation for why residual networks are preferable to non-residual ones.

Shahar Harel, Meir Maor †, Amir Ronen ‡ SparkBeyond L TD Israel Abstract We introduce generative adversarial models in which the discriminator is replaced by a calibrated (non-differentiable) classifier repeatedly enhanced by domain relevant features. The role of the classifier is to prove that the actual and generated data differ over a controlled semantic space. We demonstrate that such models have the ability to generate objects with strong guarantees on their properties in a wide range of domains. They require less data than ordinary GANs, provide natural stopping conditions, uncover important properties of the data, and enhance transfer learning. Our techniques can be combined with standard generative models. We demonstrate the usefulness of our approach by applying it to several unrelated domains: generating good locations for cellular antennae, molecule generation preserving key chemical properties, and generating and extrapolating lines from very few data points. Intriguing open problems are presented as well. 1 Introduction Generative adversarial networks (GANs) (Goodfellow et al. 2014) achieved many impressive results. Recent literature surveys as well as a large code repository can be found at (Creswell et al. 2017; Kurach et al. 2018; Hindupur). Arguably however, most of these results were obtained for generation of images, text, and videos. First, humans have very good judgment of the quality of the generated objects and hence can fine-tune the generative model until it is satisfactory. Second, there exists a huge amount of available data that can be used for model training. This is unlikely to be the case in a wide range of important domains (e.g.

We proposed a novel graph convolutional neural network that could construct a coarse, sparse latent point cloud from a dense, raw point cloud. With a novel non-isotropic convolution operation defined on irregular geometries, the model then can reconstruct the original point cloud from this latent cloud with fine details. Furthermore, we proposed that it is even possible to perform particle simulation using the latent cloud encoded from some simulated particle cloud (e.g. fluids), to accelerate the particle simulation process. Our model has been tested on ShapeNetCore dataset for Auto-Encoding with a limited latent dimension and tested on a synthesis dataset for fluids simulation. We also compare the model with other state-of-the-art models, and several visualizations were done to intuitively understand the model.

Traditional machine learning methods share a common hypothesis: training and testing datasets must be in a common feature space with the same distribution. However, in reality, the labeled target data may be rare, so that target space does not share the same feature space or distribution as an available training set (source domain). To address the mismatch of domains, we propose a Dual-Subspace Transfer Learning (DSTL) framework that considers both the common and specific information of the two domains. In DSTL, a latent common subspace is first learned to preserve the data properties and reduce the discrepancy of domains. Then, we propose a mapping strategy to transfer the sourcespecific information to the target subspace. The integration of the domain-common and specific information constructs the proposed DSTL framework. In comparison to the stateart-of works, the main contribution of our work is that the DSTL framework not only considers the commonalities, but also exploits the specific information. Experiments on three emotional speech corpora verify the effectiveness of our approach. The results show that the methods which include both domain-common and specific information perform better than the baseline methods which only exploit the domain commonalities.

This makes investment in AI one of the biggest commercial opportunities in today's fast-changing economy. However, recent Deloitte data reveals that while 82% of the UK's large businesses are pursuing some form of AI initiatives, only 15% can be considered'seasoned' or mature AI adopters – lower than the US (24%), Germany (22%), Canada (19%), Australia (17%) and France (16%). In this competitive international market, creating a favourable business environment for AI and investing in AI skills programmes is key for ensuring the long-term success of the UK's national AI strategy. While the UK has a thriving AI scene, it's important to ensure it continues to grow and that investment in AI is proportionally distributed across the country, both to make the most of existing AI talent and to encourage new talent development. Although 80% of the UK's top 50 AI start-ups are based in London, some notable AI success stories came from outside of the capital.

Now researchers at the University of Sydney have used advanced artificial intelligence and machine learning to develop a generalised method to predict when seizures will strike that will not require surgical implants. Dr Omid Kavehei from the Faculty of Engineering and IT and the University of Sydney Nano Institute said: "We are on track to develop an affordable, portable and non-surgical device that will give reliable prediction of seizures for people living with treatment-resistant epilepsy." In a paper published this month in Neural Networks, Dr Kavehei and his team have proposed a generalised, patient-specific, seizure-prediction method that can alert epilepsy sufferers within 30 minutes of the likelihood of a seizure. Dr Kavehei said there had been remarkable advances in artificial intelligence as well as micro- and nano-electronics that have allowed the development of such systems. Now it is completely accessible.

GE Healthcare signed on to a new Australian research collaboration to develop artificial intelligence tools to quickly and automatically diagnose brain aneurysms. GE will be contributing its Revolution CT scanners to the "co-creation" effort. The project is being led by the Australian division of Fujitsu, the Tokyo-based IT services firm, which will focus on developing the AI and digital solutions. Additionally, Sydney's Macquarie University and Macquarie Medical Imaging will provide clinical expertise for the product's development and testing. The group hopes to offer a commercial solution to radiology practices in Australia before going worldwide.