While conversing with chatbots, humans typically tend to ask many questions, a significant portion of which can be answered by referring to large-scale knowledge graphs (KG). While Question Answering (QA) and dialog systems have been studied independently, there is a need to study them closely to evaluate such real-world scenarios faced by bots involving both these tasks. Towards this end, we introduce the task of Complex Sequential QA which combines the two tasks of (i) answering factual questions through complex inferencing over a realistic-sized KG of millions of entities, and (ii) learning to converse through a series of coherently linked QA pairs. Through a labor intensive semi-automatic process, involving in-house and crowdsourced workers, we created a dataset containing around 200K dialogs with a total of 1.6M turns. Further, unlike existing large scale QA datasets which contain simple questions that can be answered from a single tuple, the questions in our dialogs require a larger subgraph of the KG. Specifically, our dataset has questions which require logical, quantitative, and comparative reasoning as well as their combinations. This calls for models which can: (i) parse complex natural language questions, (ii) use conversation context to resolve coreferences and ellipsis in utterances, (iii) ask for clarifications for ambiguous queries, and finally (iv) retrieve relevant subgraphs of the KG to answer such questions. However, our experiments with a combination of state of the art dialog and QA models show that they clearly do not achieve the above objectives and are inadequate for dealing with such complex real world settings. We believe that this new dataset coupled with the limitations of existing models as reported in this paper should encourage further research in Complex Sequential QA.

The task of decision-making under uncertainty is daunting, especially for problems which have significant complexity. Healthcare policy makers across the globe are facing problems under challenging constraints, with limited tools to help them make data driven decisions. In this work we frame the process of finding an optimal malaria policy as a stochastic multi-armed bandit problem, and implement three agent based strategies to explore the policy space. We apply a Gaussian Process regression to the findings of each agent, both for comparison and to account for stochastic results from simulating the spread of malaria in a fixed population. The generated policy spaces are compared with published results to give a direct reference with human expert decisions for the same simulated population. Our novel approach provides a powerful resource for policy makers, and a platform which can be readily extended to capture future more nuanced policy spaces.

Worldwide, conservation agencies employ rangers to protect conservation areas from poachers. However, agencies lack the manpower to have rangers effectively patrol these vast areas frequently. While past work has modeled poachers’ behavior so as to aid rangers in planning future patrols, those models’ predictions were not validated by extensive field tests. In my thesis, I present a spatio-temporal model that predicts poaching threat levels and results from a five-month field test in Uganda’s Queen Elizabeth Protected Area (QEPA). To my knowledge, this is the first time that a predictive model has been evaluated through such an extensive field test in this domain. These field test will be extended to another park in Uganda, Murchison Fall Protected Area, shortly. Main goals of my thesis are to develop the best performing model in terms of speed and accuracy and use such model to generate efficient and feasible patrol routes for the park rangers.

A key challenge in many reinforcement learning problems is delayed rewards, which can significantly slow down learning. Although reward shaping has previously been introduced to accelerate learning by bootstrapping an agent with additional information, this can lead to problems with convergence. We present a novel Bayesian reward shaping framework that augments the reward distribution with prior beliefs that decay with experience. Formally, we prove that under suitable conditions a Markov decision process augmented with our framework is consistent with the optimal policy of the original MDP when using the Q-learning algorithm. However, in general our method integrates seamlessly with any reinforcement learning algorithm that learns a value or action-value function through experience. Experiments are run on a gridworld and a more complex backgammon domain that show that we can learn tasks significantly faster when we specify intuitive priors on the reward distribution.

Juba recently proposed a formulation of learning abductive reasoning from examples, in which both the relative plausibility of various explanations, as well as which explanations are valid, are learned directly from data. The main shortcoming of this formulation of the task is that it assumes access to full-information (i.e., fully specified) examples; relatedly, it offers no role for declarative background knowledge, as such knowledge is rendered redundant in the abduction task by complete information. In this work we extend the formulation to utilize such partially specified examples, along with declarative background knowledge about the missing data. We show that it is possible to use implicitly learned rules together with the explicitly given declarative knowledge to support hypotheses in the course of abduction. We also show how to use knowledge in the form of graphical causal models to refine the proposed hypotheses. Finally, we observe that when a small explanation exists, it is possible to obtain a much-improved guarantee in the challenging exception-tolerant setting. Such small, human-understandable explanations are of particular interest for potential applications of the task.

A Gartner study poses that, "By 2019, IT service desks utilising machine learning enhanced technologies will free up to 30% of support capacity." In addition, Edward Carbutt, Executive Director at Marval Africa, believes the features that machine learning introduced will also add a tier of intelligent automation to traditional IT service desks. This will aid decision-making, enhancing staff productivity and opening up a level of smarter self-service for the end user. "The faster networks become, the more data is consumed and generated," says Carbutt. "In today's digital world, with its fast networks and constantly evolving technology, information is being accumulated at a rapid pace. This poses challenges for IT Service Management (ITSM) teams, who are inundated with enormous data streams, often too large to process manually. However, the application of Machine Learning to sift, sort, analyse and manage Big Data could help to simplify the tasks of ITSM."

The restricted Boltzmann machine (RBM) is one of the fundamental building blocks of deep learning. RBM finds wide applications in dimensional reduction, feature extraction, and recommender systems via modeling the probability distributions of a variety of input data including natural images, speech signals, and customer ratings, etc. We build a bridge between RBM and tensor network states (TNS) widely used in quantum many-body physics research. We devise efficient algorithms to translate an RBM into the commonly used TNS. Conversely, we give sufficient and necessary conditions to determine whether a TNS can be transformed into an RBM of given architectures. Revealing these general and constructive connections can cross-fertilize both deep learning and quantum many-body physics. Notably, by exploiting the entanglement entropy bound of TNS, we can rigorously quantify the expressive power of RBM on complex data sets. Insights into TNS and its entanglement capacity can guide the design of more powerful deep learning architectures. On the other hand, RBM can represent quantum many-body states with fewer parameters compared to TNS, which may allow more efficient classical simulations.

CAPE TOWN (Reuters) - South Africa's parliament said on Wednesday that President Jacob Zuma will deliver the state-of-the-nation address as planned on Feb 8 despite calls from within the ruling party and the opposition for the scandal-plagued leader.

In that room, Masiyiwa had a short conversation with my colleague deans of law schools of Kenyan universities. Every law school was represented. The deans of the University of Nairobi, Kenyatta University, JKUAT, Mount Kenya, CUEA, Kisii, Nazarene and Daystar were present. Riara, Egerton and Kabarak were not in attendance but they had sent their comments beforehand.

Drones, or unmanned aerial vehicles (UAV), have been used for more than three decades, but in the last few years drones are increasingly being developed and used for commercial purposes. But while inventors and entrepreneurs in Western countries struggle with strict regulations, many African countries are proving very innovative and accepting in terms of drone usage across industries. From Kigali to Khartoum, pioneers are using drones to tackle some of the continent's current challenges. In Rwanda, drones deliver blood to almost half of the country's blood transfusion centres. In Malawi, UAVs deliver HIV test kits to and from remote parts of the country.