Models, code, and papers for "George W":

##### A deep matrix factorization method for learning attribute representations

Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation. It is possible that the mapping between this new representation and our original data matrix contains rather complex hierarchical information with implicit lower-level hidden attributes, that classical one level clustering methodologies can not interpret. In this work we propose a novel model, Deep Semi-NMF, that is able to learn such hidden representations that allow themselves to an interpretation of clustering according to different, unknown attributes of a given dataset. We also present a semi-supervised version of the algorithm, named Deep WSF, that allows the use of (partial) prior information for each of the known attributes of a dataset, that allows the model to be used on datasets with mixed attribute knowledge. Finally, we show that our models are able to learn low-dimensional representations that are better suited for clustering, but also classification, outperforming Semi-Non-negative Matrix Factorization, but also other state-of-the-art methodologies variants.

* Submitted to TPAMI (16-Mar-2015)
##### Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue

We consider the problem of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. In this task, the goal is to establish universe details, and to collaborate on an interesting story in that universe, through a series of natural dialogue exchanges. Our model can augment any probabilistic conversational agent by allowing it to reason about universe information established and what potential next utterances might reveal. Ideally, with each utterance, agents would reveal just enough information to add specificity and reduce ambiguity without limiting the conversation. We empirically show that our model allows control over the rate at which the agent reveals information and that doing so significantly improves accuracy in predicting the next line of dialogues from movies. We close with a case-study with four professional theatre performers, who preferred interactions with our model-augmented agent over an unaugmented agent.

* 20 pages, 9 figures
##### Automatically tracking neurons in a moving and deforming brain

Advances in optical neuroimaging techniques now allow neural activity to be recorded with cellular resolution in awake and behaving animals. Brain motion in these recordings pose a unique challenge. The location of individual neurons must be tracked in 3D over time to accurately extract single neuron activity traces. Recordings from small invertebrates like C. elegans are especially challenging because they undergo very large brain motion and deformation during animal movement. Here we present an automated computer vision pipeline to reliably track populations of neurons with single neuron resolution in the brain of a freely moving C. elegans undergoing large motion and deformation. 3D volumetric fluorescent images of the animal's brain are straightened, aligned and registered, and the locations of neurons in the images are found via segmentation. Each neuron is then assigned an identity using a new time-independent machine-learning approach we call Neuron Registration Vector Encoding. In this approach, non-rigid point-set registration is used to match each segmented neuron in each volume with a set of reference volumes taken from throughout the recording. The way each neuron matches with the references defines a feature vector which is clustered to assign an identity to each neuron in each volume. Finally, thin-plate spline interpolation is used to correct errors in segmentation and check consistency of assigned identities. The Neuron Registration Vector Encoding approach proposed here is uniquely well suited for tracking neurons in brains undergoing large deformations. When applied to whole-brain calcium imaging recordings in freely moving C. elegans, this analysis pipeline located 150 neurons for the duration of an 8 minute recording and consistently found more neurons more quickly than manual or semi-automated approaches.

* PLoS Comput Biol 13(5): e1005517 (2017)
* 33 pages, 7 figures, code available
##### A Semi-Supervised Machine Learning Approach to Detecting Recurrent Metastatic Breast Cancer Cases Using Linked Cancer Registry and Electronic Medical Record Data

Objectives: Most cancer data sources lack information on metastatic recurrence. Electronic medical records (EMRs) and population-based cancer registries contain complementary information on cancer treatment and outcomes, yet are rarely used synergistically. To enable detection of metastatic breast cancer (MBC), we applied a semi-supervised machine learning framework to linked EMR-California Cancer Registry (CCR) data. Materials and Methods: We studied 11,459 female patients treated at Stanford Health Care who received an incident breast cancer diagnosis from 2000-2014. The dataset consisted of structured data and unstructured free-text clinical notes from EMR, linked to CCR, a component of the Surveillance, Epidemiology and End Results (SEER) database. We extracted information on metastatic disease from patient notes to infer a class label and then trained a regularized logistic regression model for MBC classification. We evaluated model performance on a gold standard set of set of 146 patients. Results: There are 495 patients with de novo stage IV MBC, 1,374 patients initially diagnosed with Stage 0-III disease had recurrent MBC, and 9,590 had no evidence of metastatis. The median follow-up time is 96.3 months (mean 97.8, standard deviation 46.7). The best-performing model incorporated both EMR and CCR features. The area under the receiver-operating characteristic curve=0.925 [95% confidence interval: 0.880-0.969], sensitivity=0.861, specificity=0.878 and overall accuracy=0.870. Discussion and Conclusion: A framework for MBC case detection combining EMR and CCR data achieved good sensitivity, specificity and discrimination without requiring expert-labeled examples. This approach enables population-based research on how patients die from cancer and may identify novel predictors of cancer recurrence.

##### Relational inductive biases, deep learning, and graph networks

Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between "hand-engineering" and "end-to-end" learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.

##### Enabling real-time multi-messenger astrophysics discoveries with deep learning

Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and the need to build a community of experts to realize the goals of multi-messenger astrophysics.

* Nature Reviews Physics volume 1, pages 600-608 (2019)
* Invited Expert Recommendation for Nature Reviews Physics. The art work produced by E. A. Huerta and Shawn Rosofsky for this article was used by Carl Conway to design the cover of the October 2019 issue of Nature Reviews Physics
##### SpotTheFake: An Initial Report on a New CNN-Enhanced Platform for Counterfeit Goods Detection

Feb 19, 2020
Alexandru Şerban, George Ilaş, George-Cosmin Poruşniuc

The counterfeit goods trade represents nowadays more than 3.3% of the whole world trade and thus it's a problem that needs now more than ever a lot of attention and a reliable solution that would reduce the negative impact it has over the modern society. This paper presents the design and early stage development of a novel counterfeit goods detection platform that makes use of the outstsanding learning capabilities of the classical VGG16 convolutional model trained through the process of "transfer learning" and a multi-stage fake detection procedure that proved to be not only reliable but also very robust in the experiments we have conducted so far using an image dataset of various goods which we gathered ourselves.

* 7 pages, 13 figures
##### Numerical Integration on Graphs: where to sample and how to weigh

Mar 19, 2018
George C. Linderman, Stefan Steinerberger

Let $G=(V,E,w)$ be a finite, connected graph with weighted edges. We are interested in the problem of finding a subset $W \subset V$ of vertices and weights $a_w$ such that $$\frac{1}{|V|}\sum_{v \in V}^{}{f(v)} \sim \sum_{w \in W}{a_w f(w)}$$ for functions $f:V \rightarrow \mathbb{R}$ that are smooth' with respect to the geometry of the graph. The main application are problems where $f$ is known to somehow depend on the underlying graph but is expensive to evaluate on even a single vertex. We prove an inequality showing that the integration problem can be rewritten as a geometric problem (the optimal packing of heat balls'). We discuss how one would construct approximate solutions of the heat ball packing problem; numerical examples demonstrate the efficiency of the method.

Feb 23, 2020
George Cevora

The influence of human judgement is ubiquitous in datasets used across the analytics industry, yet humans are known to be sub-optimal decision makers prone to various biases. Analysing biased datasets then leads to biased outcomes of the analysis. Bias by protected characteristics (e.g. race) is of particular interest as it may not only make the output of analytical process sub-optimal, but also illegal. Countering the bias by constraining the analytical outcomes to be fair is problematic because A) fairness lacks a universally accepted definition, while at the same time some definitions are mutually exclusive, and B) the use of optimisation constraints ensuring fairness is incompatible with most analytical pipelines. Both problems are solved by methods which remove bias from the data and returning an altered dataset. This approach aims to not only remove the actual bias variable (e.g. race), but also alter all proxy variables (e.g. postcode) so the bias variable is not detectable from the rest of the data. The advantage of using this approach is that the definition of fairness as a lack of detectable bias in the data (as opposed to the output of analysis) is universal and therefore solves problem (A). Furthermore, as the data is altered to remove bias the problem (B) disappears because the analytical pipelines can remain unchanged. This approach has been adopted by several technical solutions. None of them, however, seems to be satisfactory in terms of ability to remove multivariate, non-linear and non-binary biases. Therefore, in this paper I propose the concept of Fair Adversarial Networks as an easy-to-implement general method for removing bias from data. This paper demonstrates that Fair Adversarial Networks achieve this aim.

##### Neural Density Estimation and Likelihood-free Inference

Oct 29, 2019
George Papamakarios

I consider two problems in machine learning and statistics: the problem of estimating the joint probability density of a collection of random variables, known as density estimation, and the problem of inferring model parameters when their likelihood is intractable, known as likelihood-free inference. The contribution of the thesis is a set of new methods for addressing these problems that are based on recent advances in neural networks and deep learning.

* PhD thesis submitted to the University of Edinburgh in April 2019. Includes in full the following articles: arXiv:1605.06376, arXiv:1705.07057, arXiv:1805.07226
##### What can the brain teach us about building artificial intelligence?

Sep 04, 2019
Dileep George

This paper is the preprint of an invited commentary on Lake et al's Behavioral and Brain Sciences article titled "Building machines that learn and think like people". Lake et al's paper offers a timely critique on the recent accomplishments in artificial intelligence from the vantage point of human intelligence, and provides insightful suggestions about research directions for building more human-like intelligence. Since we agree with most of the points raised in that paper, we will offer a few points that are complementary.

* Behavioral and Brain Sciences, volume 40, 2017
##### Image based Eye Gaze Tracking and its Applications

Jul 09, 2019
Anjith George

Eye movements play a vital role in perceiving the world. Eye gaze can give a direct indication of the users point of attention, which can be useful in improving human-computer interaction. Gaze estimation in a non-intrusive manner can make human-computer interaction more natural. Eye tracking can be used for several applications such as fatigue detection, biometric authentication, disease diagnosis, activity recognition, alertness level estimation, gaze-contingent display, human-computer interaction, etc. Even though eye-tracking technology has been around for many decades, it has not found much use in consumer applications. The main reasons are the high cost of eye tracking hardware and lack of consumer level applications. In this work, we attempt to address these two issues. In the first part of this work, image-based algorithms are developed for gaze tracking which includes a new two-stage iris center localization algorithm. We have developed a new algorithm which works in challenging conditions such as motion blur, glint, and varying illumination levels. A person independent gaze direction classification framework using a convolutional neural network is also developed which eliminates the requirement of user-specific calibration. In the second part of this work, we have developed two applications which can benefit from eye tracking data. A new framework for biometric identification based on eye movement parameters is developed. A framework for activity recognition, using gaze data from a head-mounted eye tracker is also developed. The information from gaze data, ego-motion, and visual features are integrated to classify the activities.

* 177 pages, PhD Thesis
##### Rethinking Arithmetic for Deep Neural Networks

May 07, 2019
George A. Constantinides

We consider efficiency in deep neural networks. Hardware accelerators are gaining interest as machine learning becomes one of the drivers of high-performance computing. In these accelerators, the directed graph describing a neural network can be implemented as a directed graph describing a Boolean circuit. We make this observation precise, leading naturally to an understanding of practical neural networks as discrete functions, and show that so-called binarised neural networks are functionally complete. In general, our results suggest that it is valuable to consider Boolean circuits as neural networks, leading to the question of which circuit topologies are promising. We argue that continuity is central to generalisation in learning, explore the interaction between data coding, network topology, and node functionality for continuity, and pose some open questions for future research. As a first step to bridging the gap between continuous and Boolean views of neural network accelerators, we present some recent results from our work on LUTNet, a novel Field-Programmable Gate Array inference approach. Finally, we conclude with additional possible fruitful avenues for research bridging the continuous and discrete views of neural networks.

May 01, 2019
George Cevora

##### Role action embeddings: scalable representation of network positions

Dec 03, 2018
George Berry

We consider the question of embedding nodes with similar local neighborhoods together in embedding space, commonly referred to as "role embeddings." We propose RAE, an unsupervised framework that learns role embeddings. It combines a within-node loss function and a graph neural network (GNN) architecture to place nodes with similar local neighborhoods close in embedding space. We also propose a faster way of generating negative examples called neighbor shuffling, which quickly creates negative examples directly within batches. These techniques can be easily combined with existing GNN methods to create unsupervised role embeddings at scale. We then explore role action embeddings, which summarize the non-structural features in a node's neighborhood, leading to better performance on node classification tasks. We find that the model architecture proposed here provides strong performance on both graph and node classification tasks, in some cases competitive with semi-supervised methods.

* 7 pages, 4 figures, 5 tables
##### A Review of Network Inference Techniques for Neural Activation Time Series

Jun 20, 2018
George Panagopoulos

Studying neural connectivity is considered one of the most promising and challenging areas of modern neuroscience. The underpinnings of cognition are hidden in the way neurons interact with each other. However, our experimental methods of studying real neural connections at a microscopic level are still arduous and costly. An efficient alternative is to infer connectivity based on the neuronal activations using computational methods. A reliable method for network inference, would not only facilitate research of neural circuits without the need of laborious experiments but also reveal insights on the underlying mechanisms of the brain. In this work, we perform a review of methods for neural circuit inference given the activation time series of the neural population. Approaching it from machine learning perspective, we divide the methodologies into unsupervised and supervised learning. The methods are based on correlation metrics, probabilistic point processes, and neural networks. Furthermore, we add a data mining methodology inspired by influence estimation in social networks as a new supervised learning approach. For comparison, we use the small version of the Chalearn Connectomics competition, that is accompanied with ground truth connections between neurons. The experiments indicate that unsupervised learning methods perform better, however, supervised methods could surpass them given enough data and resources.

* 8 pages, 2 figures
##### Praaline: Integrating Tools for Speech Corpus Research

Feb 08, 2018
George Christodoulides

This paper presents Praaline, an open-source software system for managing, annotating, analysing and visualising speech corpora. Researchers working with speech corpora are often faced with multiple tools and formats, and they need to work with ever-increasing amounts of data in a collaborative way. Praaline integrates and extends existing time-proven tools for spoken corpora analysis (Praat, Sonic Visualiser and a bridge to the R statistical package) in a modular system, facilitating automation and reuse. Users are exposed to an integrated, user-friendly interface from which to access multiple tools. Corpus metadata and annotations may be stored in a database, locally or remotely, and users can define the metadata and annotation structure. Users may run a customisable cascade of analysis steps, based on plug-ins and scripts, and update the database with the results. The corpus database may be queried, to produce aggregated data-sets. Praaline is extensible using Python or C++ plug-ins, while Praat and R scripts may be executed against the corpus data. A series of visualisations, editors and plug-ins are provided. Praaline is free software, released under the GPL license.

* Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC), May 2014, Reykjavik, Iceland
##### A Person Re-Identification System For Mobile Devices

Dec 13, 2015
George Cushen

Person re-identification is a critical security task for recognizing a person across spatially disjoint sensors. Previous work can be computationally intensive and is mainly based on low-level cues extracted from RGB data and implemented on a PC for a fixed sensor network (such as traditional CCTV). We present a practical and efficient framework for mobile devices (such as smart phones and robots) where high-level semantic soft biometrics are extracted from RGB and depth data. By combining these cues, our approach attempts to provide robustness to noise, illumination, and minor variations in clothing. This mobile approach may be particularly useful for the identification of persons in areas ill-served by fixed sensors or for tasks where the sensor position and direction need to dynamically adapt to a target. Results on the BIWI dataset are preliminary but encouraging. Further evaluation and demonstration of the system will be available on our website.

* Appearing in Proceedings of the 11th IEEE/ACM International Conference on Signal Image Technology & Internet Systems (SITIS 2015)
##### Image Parsing with a Wide Range of Classes and Scene-Level Context

Oct 24, 2015
Marian George

This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood estimates at superpixels by merging likelihood scores from different probabilistic classifiers. This boosts the classification performance and enriches the representation of less-represented classes. Our second contribution consists of incorporating semantic context in the parsing process through global label costs. Our method does not rely on image retrieval sets but rather assigns a global likelihood estimate to each label, which is plugged into the overall energy function. We evaluate our system on two large-scale datasets, SIFTflow and LMSun. We achieve state-of-the-art performance on the SIFTflow dataset and near-record results on LMSun.

* Published at CVPR 2015, Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
##### Distilling Model Knowledge

Oct 08, 2015
George Papamakarios

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like to replace such cumbersome models with simpler models that perform equally well. In this thesis, we study knowledge distillation, the idea of extracting the knowledge contained in a complex model and injecting it into a more convenient model. We present a general framework for knowledge distillation, whereby a convenient model of our choosing learns how to mimic a complex model, by observing the latter's behaviour and being penalized whenever it fails to reproduce it. We develop our framework within the context of three distinct machine learning applications: (a) model compression, where we compress large discriminative models, such as ensembles of neural networks, into models of much smaller size; (b) compact predictive distributions for Bayesian inference, where we distil large bags of MCMC samples into compact predictive distributions in closed form; (c) intractable generative models, where we distil unnormalizable models such as RBMs into tractable models such as NADEs. We contribute to the state of the art with novel techniques and ideas. In model compression, we describe and implement derivative matching, which allows for better distillation when data is scarce. In compact predictive distributions, we introduce online distillation, which allows for significant savings in memory. Finally, in intractable generative models, we show how to use distilled models to robustly estimate intractable quantities of the original model, such as its intractable partition function.