https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. The book is written in an informal, accessible style, complete with pseudo-code for the most important algorithms. All topics are copiously illustrated with color images and worked examples drawn from such application domains as biology, text processing, computer vision, and robotics. Rather than providing a cookbook of different heuristic methods, the book stresses a principled model-based approach, often using the language of graphical models to specify models in a concise and intuitive way. Almost all the models described have been implemented in a MATLAB software package--PMTK (probabilistic modeling toolkit)--that is freely available online. The book is suitable for upper-level undergraduates with an introductory-level college math background and beginning graduate students.

Machine Learning : A Probabilistic Perspective

http://tinf2.vub.ac.be/~dvermeir/courses/thesis/argumentation_frameworks.pdf

On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n -person games

Landslides, movement of soil and rock under the influence of gravity, are common phenomena that cause significant human and economic losses every year. Experts use heterogeneous features such as slope, elevation, land cover, lithology, rock age, and rock family to predict landslides. To work with such features, we adapted convolutional neural networks to consider relative spatial information for the prediction task. Traditional filters in these networks either have a fixed orientation or are rotationally invariant. Intuitively, the filters should orient uphill, but there is not enough data to learn the concept of uphill; instead, it can be provided as prior knowledge. We propose a model called Locally Aligned Convolutional Neural Network, LACNN, that follows the ground surface at multiple scales to predict possible landslide occurrence for a single point. To validate our method, we created a standardized dataset of georeferenced images consisting of the heterogeneous features as inputs, and compared our method to several baselines, including linear regression, a neural network, and a convolutional network, using log-likelihood error and Receiver Operating Characteristic curves on the test set. Our model achieves 2-7% improvement in terms of accuracy and 2-15% boost in terms of log likelihood compared to the other proposed baselines.

/pdf/predicting-landslides-using-locally-aligned-convolutional-22qauqgnx6.pdf

Predicting Landslides Using Locally Aligned Convolutional Neural Networks

In this paper we show how a number of di erent formulations of nonmonotonic reasoning probabilistic reasoning and design can be combined into a coherent logic based abductive framework This framework is based on allowing consistent assumptions to be used to prove a goal Di erent frameworks are characterised by who chooses the assumptions whether an adversary chooses the assumptions na ture chooses the assumptions or one gets to choose whatever assump tions one likes

/pdf/who-chooses-the-assumptions-2crmevnvbq.pdf

Who chooses the assumptions

When using Bayesian networks, practitioners often express constraints among variables by conditioning a common child node to induce the desired distribution. For example, an `or' constraint can be easily expressed by a node modelling a logical `or' of its parents' values being conditioned to true. This has the desired effect that at least one parent must be true. However, conditioning also alters the distributions of further ancestors in the network. In this paper we argue that these side effectsare undesirable when constraints are added during model design. We describe a method called shielding to remove these side effects while remaining within the directed language of Bayesian networks. This method is then compared to chain graphs which allow undirected and directed edges and which model equivalent distributions. Thus, in addition to solving this common modelling problem, shielded Bayesian networks provide a novel method for implementing chain graphs with existing Bayesian network tools.

/pdf/adding-local-constraints-to-bayesian-networks-2tm6on8xdf.pdf

Adding Local Constraints to Bayesian Networks

The Bayesian network is a powerful knowledge representation formalism; it is also capable of improving its precision through experience. Spiegelhalter et al. [1989] proposed a procedure for sequential updating forward conditional probabilities (FCP) in Bayesian networks of diameter 1 with a single parent node. The procedure assumes certainty for each diagnosis which is not practical for many applications. In this paper we present a new algorithm (ALPP) that allows refinement of FCPs based on expert estimates of posterior probability. ALPP applies to any DAG of diameter 1. Fast convergence is achieved. Simulation results compare ALPP with Spiegelhalter’s method.

Sequential updating conditional probability in Bayesian networks by posterior probability

Rather than attacking the main premise of Cheeseman’s paper, namely that we need to do some form of probabilistic reasoning to do commonsense reasoning, which we agree with, we would like to comment on the implied premise that there is some competition between logical and probabilistic reasoning. We would like to argue that these can, and indeed should, coexist in the same framework. Rather than claim that one or the other is the formalism of choice for commonsense reasoning, we say that both are useful tools for many of the problems of AI. In essence we argue that the appropriate way to use logic is in the form of theory formation, and the appropriate role of probability is as a theory comparator.

David Poole

Papers

Predicting Landslides Using Locally Aligned Convolutional Neural Networks

Who chooses the assumptions

Adding Local Constraints to Bayesian Networks

Sequential updating conditional probability in Bayesian networks by posterior probability

Combining logic and probability