In personalised decision making, evidence is required to determine suitable actions for individuals. Such evidence can be obtained by identifying treatment effect heterogeneity in different subgroups of the population. In this paper, we design a new type of pattern, treatment effect pattern to represent and discover treatment effect heterogeneity from data for determining whether a treatment will work for an individual or not. Our purpose is to use the computational power to find the most specific and relevant conditions for individuals with respect to a treatment or an action to assist with personalised decision making. Most existing work on identifying treatment effect heterogeneity takes a top-down or partitioning based approach to search for subgroups with heterogeneous treatment effects. We propose a bottom-up generalisation algorithm to obtain the most specific patterns that fit individual circumstances the best for personalised decision making. For the generalisation, we follow a consistency driven strategy to maintain inner-group homogeneity and inter-group heterogeneity of treatment effects. We also employ graphical causal modelling technique to identify adjustment variables for reliable treatment effect pattern discovery. Our method can find the treatment effect patterns reliably as validated by the experiments. The method is faster than the two existing machine learning methods for heterogeneous treatment effect identification and it produces subgroups with higher inner-group treatment effect homogeneity.

The deep layers of modern neural networks extract a rather rich set of features as an input propagates through the network. This paper sets out to harvest these rich intermediate representations for quantization with minimal accuracy loss while significantly reducing the memory footprint and compute intensity of the DNN. This paper utilizes knowledge distillation through teacher-student paradigm (Hinton et al., 2015) in a novel setting that exploits the feature extraction capability of DNNs for higher-accuracy quantization. As such, our algorithm logically divides a pretrained full-precision DNN to multiple sections, each of which exposes intermediate features to train a team of students independently in the quantized domain. This divide and conquer strategy, in fact, makes the training of each student section possible in isolation while all these independently trained sections are later stitched together to form the equivalent fully quantized network. Experiments on various DNNs (LeNet, ResNet-20, SVHN and VGG-11) show that, on average, this approach - called DCQ (Divide and Conquer Quantization) - achieves on average 9.7% accuracy improvement to a state-of-the-art quantized training technique, DoReFa (Zhou et al., 2016) for binary and ternary networks.

Gamers rarely get to hear the thwack of virtual leather on willow these days. But in the midst of a huge summer for cricket in the UK, with the World Cup followed by an Ashes series, Australian developer Big Ant Studios has stepped into the breach. Cricket 19 has a great career mode that lets you work your way up from club cricket, or take control of an established pro. In each game, you can either control your player alone or their entire team. There are playable scenarios from famous real-life games, and a welter of editing tools that let you design your own custom competitions, bats and cricket grounds.

IBM (NYSE: IBM) today announced the first recipients and list of global women leaders and pioneers in AI for business. The list recognizes and celebrates women across a variety of industries and geographies for pioneering the use of AI to advance their companies in areas such as innovation, growth, and transformation. IBM will celebrate the honorees during an inaugural recognition event on June 12, 2019 at the IBM Watson Experience Center in New York, New York where the women will share their experiences leading AI initiatives in their organizations. Students from IBM's P-Tech program will attend to hear from these leaders who have applied AI technology in diverse and meaningful ways to help drive business innovation. "Artificial Intelligence is poised to drive dramatic advances in every industry," said Michelle Peluso, SVP, Digital Sales & CMO, IBM, who also serves as Leader of IBM's Women's Initiative.

The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive, and large-scale. Machine learning, or more specifically deep reinforcement learning (DRL), methods have been proposed widely to address these issues. By incorporating deep learning into traditional RL, DRL is highly capable of solving complex, dynamic, and especially high-dimensional cyber defense problems. This paper presents a survey of DRL approaches developed for cyber security. We touch on different vital aspects, including DRL-based security methods for cyber-physical systems, autonomous intrusion detection techniques, and multi-agent DRL-based game theory simulations for defense strategies against cyber attacks. Extensive discussions and future research directions on DRL-based cyber security are also given. We expect that this comprehensive review provides the foundations for and facilitates future studies on exploring the potential of emerging DRL to cope with increasingly complex cyber security problems.

The recent application of Deep Learning in various areas of medical image analysis has brought excellent performance gain. The application of deep learning technologies in medical image registration successfully outperformed traditional optimization based registration algorithms both in registration time and accuracy. In this paper, we present a densely connected convolutional architecture for deformable image registration. The training of the network is unsupervised and does not require ground-truth deformation or any synthetic deformation as a label. The proposed architecture is trained and tested on two different version of tissue cleared data, 10\% and 25\% resolution of high resolution dataset respectively and demonstrated comparable registration performance with the state-of-the-art ANTS registration method. The proposed method is also compared with the deep-learning based Voxelmorph registration method. Due to the memory limitation, original voxelmorph can work at most 15\% resolution of Tissue cleared data. For rigorous experimental comparison we developed a patch-based version of Voxelmorph network, and trained it on 10\% and 25\% resolution. In both resolution, proposed DenseDeformation network outperformed Voxelmorph in registration accuracy.

The Western Australia Police Force (WAPF) has been piloting an Australian-developed cloud AI-based solution for managing the vast troves of data seized in cases involving digital evidence. Manually sorting through it all is a time-consuming task, and it can be easy to miss information and connections. WAPF has taken steps to address this issue by trialling a data and AI platform developed by Victoria's Modis. The trial, conducted in collaboration with Microsoft, has involved using Azure-based cognitive services to collect and efficiently analyse data, and to manage translations into English. The Data & AI solution is designed to use AI techniques to ingest and analyse large qualities of information collected during an investigation, helping investigators make sense of the evidence and find critical connections.

We explore using latent natural language instructions as an expressive and compositional representation of complex actions for hierarchical decision making. Rather than directly selecting micro-actions, our agent first generates a latent plan in natural language, which is then executed by a separate model. We introduce a challenging real-time strategy game environment in which the actions of a large number of units must be coordinated across long time scales. We gather a dataset of 76 thousand pairs of instructions and executions from human play, and train instructor and executor models. Experiments show that models using natural language as a latent variable significantly outperform models that directly imitate human actions. The compositional structure of language proves crucial to its effectiveness for action representation. We also release our code, models and data.

Collaborative representation is a popular feature learning approach, which encoding process is assisted by variety types of information. In this paper, we propose a collaborative representation restricted Boltzmann Machine (CRRBM) for modeling binary data and a collaborative representation Gaussian restricted Boltzmann Machine (CRGRBM) for modeling realvalued data by applying a collaborative representation strategy in the encoding procedure. We utilize Locality Sensitive Hashing (LSH) to generate similar sample subsets of the instance and observed feature set simultaneously from input data. Hence, we can obtain some mini blocks, which come from the intersection of instance and observed feature subsets. Then we integrate Contrastive Divergence and Bregman Divergence methods with mini blocks to optimize our CRRBM and CRGRBM models. In their training process, the complex collaborative relationships between multiple instances and features are fused into the hidden layer encoding. Hence, these encodings have dual characteristics of concealment and cooperation. Here, we develop two deep collaborative encoder frameworks (DCEF) based on the CRRBM and CRGRBM models: one is a DCEF with Gaussian linear visible units (GDCEF) for modeling real-valued data, and the other is a DCEF with binary visible units (BDCEF) for modeling binary data. We explore the collaborative representation capability of the hidden features in every layer of the GDCEF and BDCEF framework, especially in the deepest hidden layer. The experimental results show that the GDCEF and BDCEF frameworks have more outstanding performances than the classic Autoencoder framework for unsupervised clustering task on the MSRA-MM2.0 and UCI datasets, respectively.

This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning representations of words called Multiview Latent Semantic Analysis (MVLSA). By incorporating up to 46 different types of co-occurrence statistics for the same vocabulary of english words, I show that MVLSA outperforms other state-of-the-art word embedding models. Next, I focus on learning entity representations for search and recommendation and present the second method of this thesis, Neural Variational Set Expansion (NVSE). NVSE is also an unsupervised learning method, but it is based on the Variational Autoencoder framework. Evaluations with human annotators show that NVSE can facilitate better search and recommendation of information gathered from noisy, automatic annotation of unstructured natural language corpora. Finally, I move from unstructured data and focus on structured knowledge graphs. I present novel approaches for learning embeddings of vertices and edges in a knowledge graph that obey logical constraints.