Models, code, and papers for "Jamie Hall":

Towards a Human-like Open-Domain Chatbot

Jan 31, 2020
Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, Quoc V. Le

We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. We also propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of a human-like multi-turn conversation. Our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher in absolute SSA than the existing chatbots we evaluated.

* 38 pages, 12 figures 

  Click for Model/Code and Paper
Kidney and Kidney Tumor Segmentation using a Logical Ensemble of U-nets with Volumetric Validation

Aug 07, 2019
Jamie A. O'Reilly, Manas Sangworasil, Takenobu Matsuura

Automated medical image segmentation is a priority research area for computational methods. In particular, detection of cancerous tumors represents a current challenge in this area with potential for real-world impact. This paper describes a method developed in response to the 2019 Kidney Tumor Segmentation Challenge (KiTS19). Axial computed tomography (CT) scans from 210 kidney cancer patients were used to develop and evaluate this automatic segmentation method based on a logical ensemble of fully-convolutional network (FCN) architectures, followed by volumetric validation. Data was pre-processed using conventional computer vision techniques, thresholding, histogram equalization, morphological operations, centering, zooming and resizing. Three binary FCN segmentation models were trained to classify kidney and tumor (2), and only tumor (1), respectively. Model output images were stacked and volumetrically validated to produce the final segmentation for each patient scan. The average F1 score from kidney and tumor pixel classifications was calculated as 0.6758 using preprocessed images and annotations; although restoring to the original image format reduced this score. It remains to be seen how this compares to other solutions.

* 9 pages, 4 figures, 1 table, competition submission manuscript 

  Click for Model/Code and Paper
Immune System Approaches to Intrusion Detection - A Review (ICARIS)

May 30, 2013
Uwe Aickelin, Julie Greensmith, Jamie Twycross

The use of artificial immune systems in intrusion detection is an appealing concept for two reasons. Firstly, the human immune system provides the human body with a high level of protection from invading pathogens, in a robust, self-organised and distributed manner. Secondly, current techniques used in computer security are not able to cope with the dynamic and increasingly complex nature of computer systems and their security. It is hoped that biologically inspired approaches in this area, including the use of immune-based systems will be able to meet this challenge. Here we collate the algorithms used, the development of the systems and the outcome of their implementation. It provides an introduction and review of the key developments within this field, in addition to making suggestions for future research.

* Proceedings of the 3rd International Conference on Artificial Immune Systems (ICARIS), 316-329, 2004 

  Click for Model/Code and Paper
Detecting Danger: Applying a Novel Immunological Concept to Intrusion Detection Systems

Feb 03, 2010
Julie Greensmith, Uwe Aickelin, Jamie Twycross

In recent years computer systems have become increasingly complex and consequently the challenge of protecting these systems has become increasingly difficult. Various techniques have been implemented to counteract the misuse of computer systems in the form of firewalls, anti-virus software and intrusion detection systems. The complexity of networks and dynamic nature of computer systems leaves current methods with significant room for improvement. Computer scientists have recently drawn inspiration from mechanisms found in biological systems and, in the context of computer security, have focused on the human immune system (HIS). The human immune system provides a high level of protection from constant attacks. By examining the precise mechanisms of the human immune system, it is hoped the paradigm will improve the performance of real intrusion detection systems. This paper presents an introduction to recent developments in the field of immunology. It discusses the incorporation of a novel immunological paradigm, Danger Theory, and how this concept is inspiring artificial immune systems (AIS). Applications within the context of computer security are outlined drawing direct reference to the underlying principles of Danger Theory and finally, the current state of intrusion detection systems is discussed and improvements suggested.

* Proceedings of The 6th International Conference in Adaptive Computing in Design and Manufacture (ACDM2004), Bristol, UK 
* 3 pages, The 6th International Conference in Adaptive Computing in Design and Manufacture (ACDM2004), Bristol, UK 

  Click for Model/Code and Paper
Guarantees for Spectral Clustering with Fairness Constraints

Jan 24, 2019
Matthäus Kleindessner, Samira Samadi, Pranjal Awasthi, Jamie Morgenstern

Given the widespread popularity of spectral clustering (SC) for partitioning graph data, we study a version of constrained SC in which we try to incorporate the fairness notion proposed by Chierichetti et al. (2017). According to this notion, a clustering is fair if every demographic group is approximately proportionally represented in each cluster. To this end, we develop variants of both normalized and unnormalized constrained SC and show that they help find fairer clusterings on both synthetic and real data. We also provide a rigorous theoretical analysis of our algorithms. While there have been efforts to incorporate various constraints into the SC framework, theoretically analyzing them is a challenging problem. We overcome this by proposing a natural variant of the stochastic block model where h groups have strong inter-group connectivity, but also exhibit a "natural" clustering structure which is fair. We prove that our algorithms can recover this fair clustering with high probability.


  Click for Model/Code and Paper
ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning

Feb 12, 2019
Harris Chan, Yuhuai Wu, Jamie Kiros, Sanja Fidler, Jimmy Ba

Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and universal goal representation. We present Augmenting experienCe via TeacheR's adviCE (ACTRCE), an efficient reinforcement learning technique that extends the HER framework using natural language as the goal representation. We first analyze the differences among goal representation, and show that ACTRCE can efficiently solve difficult reinforcement learning problems in challenging 3D navigation tasks, whereas HER with non-language goal representation failed to learn. We also show that with language goal representations, the agent can generalize to unseen instructions, and even generalize to instructions with unseen lexicons. We further demonstrate it is crucial to use hindsight advice to solve challenging tasks, and even small amount of advice is sufficient for the agent to achieve good performance.


  Click for Model/Code and Paper
PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning

Apr 11, 2017
Alexander Krull, Eric Brachmann, Sebastian Nowozin, Frank Michel, Jamie Shotton, Carsten Rother

State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are non-differentiable. As a result, these algorithms are hard to train in an end-to-end fashion. In this work we propose to learn an efficient algorithm for the task of 6D object pose estimation. Our system optimizes the parameters of an existing state-of-the art pose estimation system using reinforcement learning, where the pose estimation system now becomes the stochastic policy, parametrized by a CNN. Additionally, we present an efficient training algorithm that dramatically reduces computation time. We show empirically that our learned pose estimation procedure makes better use of limited resources and improves upon the state-of-the-art on a challenging dataset. Our approach enables differentiable end-to-end training of complex algorithmic pipelines and learns to make optimal use of a given computational budget.


  Click for Model/Code and Paper
Depth-based hand pose estimation: methods, data, and challenges

May 06, 2015
James Steven Supancic III, Gregory Rogez, Yi Yang, Jamie Shotton, Deva Ramanan

Hand pose estimation has matured rapidly in recent years. The introduction of commodity depth sensors and a multitude of practical applications have spurred new advances. We provide an extensive analysis of the state-of-the-art, focusing on hand pose estimation from a single depth frame. To do so, we have implemented a considerable number of systems, and will release all software and evaluation code. We summarize important conclusions here: (1) Pose estimation appears roughly solved for scenes with isolated hands. However, methods still struggle to analyze cluttered scenes where hands may be interacting with nearby objects and surfaces. To spur further progress we introduce a challenging new dataset with diverse, cluttered scenes. (2) Many methods evaluate themselves with disparate criteria, making comparisons difficult. We define a consistent evaluation criteria, rigorously motivated by human experiments. (3) We introduce a simple nearest-neighbor baseline that outperforms most existing systems. This implies that most systems do not generalize beyond their training sets. This also reinforces the under-appreciated point that training data is as important as the model itself. We conclude with directions for future progress.


  Click for Model/Code and Paper
Immune System Approaches to Intrusion Detection - A Review

Apr 08, 2008
Jungwon Kim, Peter J. Bentley, Uwe Aickelin, Julie Greensmith, Gianni Tedesco, Jamie Twycross

The use of artificial immune systems in intrusion detection is an appealing concept for two reasons. Firstly, the human immune system provides the human body with a high level of protection from invading pathogens, in a robust, self-organised and distributed manner. Secondly, current techniques used in computer security are not able to cope with the dynamic and increasingly complex nature of computer systems and their security. It is hoped that biologically inspired approaches in this area, including the use of immune-based systems will be able to meet this challenge. Here we review the algorithms used, the development of the systems and the outcome of their implementation. We provide an introduction and analysis of the key developments within this field, in addition to making suggestions for future research.

* Natural Computing, 6(4), pp 413-466, 2007 

  Click for Model/Code and Paper
FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning

Apr 10, 2019
Ángel Alexander Cabrera, Will Epperson, Fred Hohman, Minsuk Kahng, Jamie Morgenstern, Duen Horng Chau

The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or exacerbate implicit and explicit societal biases into their outputs, disadvantaging certain demographic subgroups. Discovering which biases a machine learning model has introduced is a great challenge, due to the numerous definitions of fairness and the large number of potentially impacted subgroups. We present FairVis, a mixed-initiative visual analytics system that integrates a novel subgroup discovery technique for users to audit the fairness of machine learning models. Through FairVis, users can apply domain knowledge to generate and investigate known subgroups, and explore suggested and similar subgroups. FairVis' coordinated views enable users to explore a high-level overview of subgroup performance and subsequently drill down into detailed investigation of specific subgroups. We show how FairVis helps to discover biases in two real datasets used in predicting income and recidivism. As a visual analytics system devoted to discovering bias in machine learning, FairVis demonstrates how interactive visualization may help data scientists and the general public in understanding and creating more equitable algorithmic systems.

* Under review 

  Click for Model/Code and Paper
Learning Memory Access Patterns

Mar 06, 2018
Milad Hashemi, Kevin Swersky, Jamie A. Smith, Grant Ayers, Heiner Litz, Jichuan Chang, Christos Kozyrakis, Parthasarathy Ranganathan

The explosion in workload complexity and the recent slow-down in Moore's law scaling call for new approaches towards efficient computing. Researchers are now beginning to use recent advances in machine learning in software optimizations, augmenting or replacing traditional heuristics and data structures. However, the space of machine learning for computer hardware architecture is only lightly explored. In this paper, we demonstrate the potential of deep learning to address the von Neumann bottleneck of memory performance. We focus on the critical problem of learning memory access patterns, with the goal of constructing accurate and efficient memory prefetchers. We relate contemporary prefetching strategies to n-gram models in natural language processing, and show how recurrent neural networks can serve as a drop-in replacement. On a suite of challenging benchmark datasets, we find that neural networks consistently demonstrate superior performance in terms of precision and recall. This work represents the first step towards practical neural-network based prefetching, and opens a wide range of exciting directions for machine learning in computer architecture research.


  Click for Model/Code and Paper
Algorithms and Statistical Models for Scientific Discovery in the Petabyte Era

Nov 05, 2019
Brian Nord, Andrew J. Connolly, Jamie Kinney, Jeremy Kubica, Gautaum Narayan, Joshua E. G. Peek, Chad Schafer, Erik J. Tollerud, Camille Avestruz, G. Jogesh Babu, Simon Birrer, Douglas Burke, João Caldeira, Douglas A. Caldwell, Joleen K. Carlberg, Yen-Chi Chen, Chuanfei Dong, Eric D. Feigelson, V. Zach Golkhou, Vinay Kashyap, T. S. Li, Thomas Loredo, Luisa Lucie-Smith, Kaisey S. Mandel, J. R. Martínez-Galarza, Adam A. Miller, Priyamvada Natarajan, Michelle Ntampaka, Andy Ptak, David Rapetti, Lior Shamir, Aneta Siemiginowska, Brigitta M. Sipőcz, Arfon M. Smith, Nhan Tran, Ricardo Vilalta, Lucianne M. Walkowicz, John ZuHone

The field of astronomy has arrived at a turning point in terms of size and complexity of both datasets and scientific collaboration. Commensurately, algorithms and statistical models have begun to adapt --- e.g., via the onset of artificial intelligence --- which itself presents new challenges and opportunities for growth. This white paper aims to offer guidance and ideas for how we can evolve our technical and collaborative frameworks to promote efficient algorithmic development and take advantage of opportunities for scientific discovery in the petabyte era. We discuss challenges for discovery in large and complex data sets; challenges and requirements for the next stage of development of statistical methodologies and algorithmic tool sets; how we might change our paradigms of collaboration and education; and the ethical implications of scientists' contributions to widely applicable algorithms and computational modeling. We start with six distinct recommendations that are supported by the commentary following them. This white paper is related to a larger corpus of effort that has taken place within and around the Petabytes to Science Workshops (https://petabytestoscience.github.io/).

* arXiv admin note: substantial text overlap with arXiv:1905.05116 

  Click for Model/Code and Paper