DOCSLIB.ORG

Neural Network Tools: an Overview from Work on "Automatic Classification of Alzheimer’S Disease from Structural MRI" Report for Master’S Thesis

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Neural Network Tools: an Overview from Work on Neural Network Tools: An Overview From work on "Automatic Classification of Alzheimer’s Disease from Structural MRI" Report for Master’s Thesis Eivind Arvesen Østfold University College [email protected] Abstract Machine learning has exploded in popularity during the last decade, and neural networks in particular have seen a resurgence due to the advent of deep learning. In this paper, we examine modern neural network software-libraries and describe the main differences between them, as well as their strengths and weaknesses. 1 Introduction at The University of Montreal, built with re- search in mind. It has a particular focus on The field of machine learning is now more al- deep learning. The library is focused on easy luring than ever, helping researchers and busi- configurability for expert users (i.e. machine nesses to tackle a variety of challenging prob- learning researchers) —unlike "black-box" li- lems such as development of autonomous vehi- braries, which provide good performance with- cles, visual recognition systems and computer- out demanding knowledge about underlying al- aided diagnosis. There is a plethora of different gorithms from users. One way to put it would tools and libraries available that aim to make be that the library values ease of experimenta- work on machine learning problems easier for tion over ease of use. users, and while most of the more general alter- natives are quite similar in terms of functional- Though Pylearn2 assumes some technical ity, they nonetheless differ in terms of approach sophistication on the part of users, the library and design goals. also has a focus on reusability, and the re- This report describes several popular ma- sulting modularity makes it possible to com- chine learning tools, attempts to showcase their bine and adapt several re-usable components strengths and characterizes situations in which to form working models, and to only learn they would be well suited for use. The primary about the parts of the library one wants to use. focus is on modern tools; Most of these will One of the library’s goals is to contain refer- have some connection to deep learning, as it is ence implementations of all models and algo- an approach that is currently producing many rithms published by the LISA-lab, and it has state of the art results in fields like computer been used to set the state of the art on several vision. standardized datasets, including a test error of 0.45% on MNIST in 2013 [3] —the best per- formance without data augmentation at that 2 Tools point —using a convolutional maxout-network with dropout regularization. 2.1 Pylearn2 Pylearn2 makes use of a YAML2-interface, Pylearn2 [4] is a cutting edge machine learning which allows users to set up and perform ex- library for Python developed at the LISA-lab1 periments rapidly by defining their models in 1One of recent years’ most prominent labs, spearheaded by one of the leading researchers on deep learning, Yoshua Bengio. 2A human-readable data serialization format. 1 an almost declarative style, using (pre-)defined to-use standardized benchmark datasets (such components as building blocks and specifying as MNIST and CIFAR-10) and unsupervised hyperparameters. Alternatively, experiments learning out of the box. It appears to be grow- may also be specified through a Python script. ing steadily in popularity, and is apparently The library is built upon the Theano library popular amongst contestants in Kaggle con- —a numerical computation library for Python tests. and C/CUDA-compiler —which is also devel- oped at the LISA-lab. Theano can also com- 2.2 Torch pute gradients automatically; Users need only specify architecture and loss function. This Torch [1] is an open source scientific comput- makes it very easy to experiment quickly. ing framework that supports many different GPU-based models are also enabled via machine learning algorithms. It uses a JIT compilation with Theano, as it can compile compilation-based implementation of the Lua- both to GPU and CPU. Pylearn2 also provides language for ease of use and efficiency, on top of wrappers to widely used and efficient third- a C/CUDA-implementation. Torch7 (its cur- party GPU-implementations of convolutional rent version) is currently in use at and being nets like CUDA-convnet and Caffe. contributed to by DeepMind (Google), Face- As the library is under heavy develop- book, Twitter and New York University, ac- ment, its documentation is somewhat sparse, cording to the project’s website5. although the source code itself is thoroughly It is somewhat similar and comparable to commented. Though its website has a few note- Theano/Pylearn2 (used in conjunction with book3-style and short examples, users will likely Numpy and the rest of the packages in the have to spend some amount of time reading "standard" Python scientific stack), complete source code to figure out how to implement with suitable datatypes which supports math- their own models and extensions, as well as ematical operations, stastistical distributions, how to integrate them (for use) with the library. and BLAS6 operations, as well as supporting Pylearn2 can thereby be somewhat hard to un- rapid experimentation via a REPL7. It is also derstand, extend, modify and debug for begin- composed of reusable parts that can be com- ners. There is, however, a very active commu- bined in many variations. Torch also has a nity around the library, including usergroups/- large ecosystem of community-driven packages, mailinglists and the official source code repos- and as with Pylearn2, other packages brings itory4. Despite its somewhat steep learning- support for things like image processing —in- curve, Pylearn2 is very powerful. cluding a relatively recently released package8 Pylearn2 is to a large extent created and of CUDA extensions for deep learning by Face- supported by it’s users (students at the LISA- book AI Research. lab and other contributors), and since it has its Torch allows neural network models to be focus on research, features are added as they are run on GPUs through the help of CUDA. This needed, meaning that users will likely have to can be achieved by users via simple typecasting. code up some things themselves —unless they Like Pylearn2, Torch7 includes scripts to are only trying to replicate published results or load several popular datasets. Third party run variations on old experiments/datasets. loaders are also available for datasets other than Pylearn2 comes with support for/ready- those that are supported by default. 3A web-based (locally interactive) environment provided by the enhanced Python-shell and -project IPython. 4Available at https://github.com/lisa-lab/pylearn2 5http://torch.ch 6Basic Linear Algebra Subprograms 7Read–eval–print loop, i.e. an interactive shell 8Available at https://github.com/facebook/fbcunn 2 According to a 2011 paper [2] by some dustry and academia, and it is therefore easier of Torch’s maintainers, Torch7 was faster to find helpful tips and snippets of code online, than Theano on most benchmarks. The au- as there is a larger userbase (and indeed more thor’s noted, however, that Theano was "faster use cases, as it is a language of its own). Mat- than any existing implementation" (including lab also includes integrated development envi- Torch5, Matlab with GPUmat and EBLearn), ronment. going as far as saying that it crushed the al- ternatives in benchmarks when run on a GPU. 2.4 Scikit-learn It is also important to remember, as the au- thors comment, that only larger network archi- Scikit-learn [7] is another machine learning li- tectures will benefit from GPU-acceleration. brary for Python. Building upon widely used In the realm of deployment, Torch may packages like numpy (N-dimensional arrays) prove to be easier in use than for instance and scipy (scientific computing), it contains a Pylearn2 (and MATLAB, which only supports variety of classification, regression and clus- deployment of pre-trained networks), as the Lu- tering algorithms, providing machine learn- aJIT environment is embeddable into a host of ing techniques for supervised and unsupervised environments, including smart-phone applica- problems. The package "focuses on bringing tions and video games. machine learning to non-specialists" [7], and Torch is very practical to use for deep learn- is thus more accessible than some alternatives. ing, as the library has a focus on these ap- It does therefore, unlike Pylearn2, not require proaches. Like Pylearn2, Torch has an active users to possess knowledge of the models’ im- community, including mailing lists/user groups, plementations. Also unlike Pylearn2, which fo- community wiki, online chat and an official cuses mostly on neural networks, scikit-learn source code repository on github. has a wide varity of machine learning tech- niques available, including support vector ma- chines, logistic regression, nearest neighbors 2.3 Matlab Neural Network Toolbox and random forest, covering tasks like classi- fication, regression, clustering, dimensionality Matlab supports Neural Networks via the Neu- reduction, model selection and preprocessing. ral Network Toolbox, and networks built with The libraries website includes comprehensive this can in turn be parallelized and run on documentation. It includes limited support for GPUs when used in conjunction with the Par- neural networks, but it is not very practical to allel Computing Toolbox. use for deep learning. While it is not supported "out of the box", deep learning architectures can be used in Mat- 2.5 Weka lab via the Deep Learning Toolbox9 third-party software. The toolbox includes support for Weka is machine learning software [5] from the Deep Belief Nets, Stacked Autoencoders, Con- University of Waikato, New Zealand, written volutional Neural Nets, Convolutional Autoen- with focus on data mining. It is written in Java, coders and Feedforward Backpropagation Neu- and is usable on its own (through it’s GUI "ex- ral Nets.
Load more

Recommended publications
  • Spectrally-Based Audio Distances Are Bad at Pitch
    I’m Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch Joseph Turian Max Henry [email protected] [email protected] Abstract Growing research demonstrates that synthetic failure modes imply poor generaliza- tion. We compare commonly used audio-to-audio losses on a synthetic benchmark, measuring the pitch distance between two stationary sinusoids. The results are sur- prising: many have poor sense of pitch direction. These shortcomings are exposed using simple rank assumptions. Our task is trivial for humans but difficult for these audio distances, suggesting significant progress can be made in self-supervised audio learning by improving current losses. 1 Introduction Rather than a physical quantity contained in the signal, pitch is a percept that is strongly correlated with the fundamental frequency of a sound. While physically elusive, pitch is a natural dimension to consider when comparing sounds. Children as young as 8 months old are sensitive to melodic contour [65], implying that an early and innate sense of relative pitch is important to parsing our auditory experience. This basic ability is distinct from the acute pitch sensitivity of professional musicians, which improves as a function of musical training [36]. Pitch is important to both music and speech signals. Typically, speech pitch is more narrowly circumscribed than music, having a range of 70–1000Hz, compared to music which spans roughly the range of a grand piano, 30–4000Hz [31]. Pitch in speech signals also fluctuates more rapidly [6]. In tonal languages, pitch has a direct influence on the meaning of words [8, 73, 76]. For non-tone languages such as English, pitch is used to infer (supra-segmental) prosodic and speaker-dependent features [19, 21, 76].
    [Show full text]
  • Arxiv:2008.01352V3 [Cs.LG] 23 Mar 2021 Spatiotemporal Disentanglement in the PDE Formalism
    Published as a conference paper at ICLR 2021 PDE-DRIVEN SPATIOTEMPORAL DISENTANGLEMENT Jérémie Donà,y∗ Jean-Yves Franceschi,y∗ Sylvain Lampriery & Patrick Gallinariyz ySorbonne Université, CNRS, LIP6, F-75005 Paris, France zCriteo AI Lab, Paris, France [email protected] ABSTRACT A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory. Following this direction, we propose in this article a novel and general paradigm for this task based on a resolution method for partial differential equations: the separation of variables. This inspiration allows us to introduce a dynamical interpretation of spatiotemporal disentanglement. It induces a principled model based on learning disentangled spatial and temporal representations of a phenomenon to accurately predict future observations. We experimentally demonstrate the performance and broad applicability of our method against prior state-of-the-art models on physical and synthetic video datasets. 1 INTRODUCTION The interest of the machine learning community in physical phenomena has substantially grown for the last few years (Shi et al., 2015; Long et al., 2018; Greydanus et al., 2019). In particular, an increasing amount of works studies the challenging problem of modeling the evolution of dynamical systems, with applications in sensible domains like climate or health science, making the understanding of physical phenomena a key challenge in machine learning. To this end, the community has successfully leveraged the formalism of dynamical systems and their associated differential formulation as powerful tools to specifically design efficient prediction models. In this work, we aim at studying this prediction problem with a principled and general approach, through the prism of Partial Differential Equations (PDEs), with a focus on learning spatiotemporal disentangled representations.
    [Show full text]
  • Large Margin Deep Networks for Classification
    Large Margin Deep Networks for Classification Gamaleldin F. Elsayed ∗ Dilip Krishnan Hossein Mobahi Kevin Regan Google Research Google Research Google Research Google Research Samy Bengio Google Research {gamaleldin, dilipkay, hmobahi, kevinregan, bengio}@google.com Abstract We present a formulation of deep learning that aims at producing a large margin classifier. The notion of margin, minimum distance to a decision boundary, has served as the foundation of several theoretically profound and empirically suc- cessful results for both classification and regression tasks. However, most large margin algorithms are applicable only to shallow models with a preset feature representation; and conventional margin methods for neural networks only enforce margin at the output layer. Such methods are therefore not well suited for deep networks. In this work, we propose a novel loss function to impose a margin on any chosen set of layers of a deep network (including input and hidden layers). Our formulation allows choosing any lp norm (p ≥ 1) on the metric measuring the margin. We demonstrate that the decision boundary obtained by our loss has nice properties compared to standard classification loss functions. Specifically, we show improved empirical results on the MNIST, CIFAR-10 and ImageNet datasets on multiple tasks: generalization from small training sets, corrupted labels, and robustness against adversarial perturbations. The resulting loss is general and complementary to existing data augmentation (such as random/adversarial input transform) and regularization techniques such as weight decay, dropout, and batch norm. 2 1 Introduction The large margin principle has played a key role in the course of machine learning history, producing remarkable theoretical and empirical results for classification (Vapnik, 1995) and regression problems (Drucker et al., 1997).
    [Show full text]
  • Reverse Image Search for Scientific Data Within and Beyond the Visible
    Journal, Vol. XXI, No. 1, 1-5, 2013 Additional note Reverse Image Search for Scientific Data within and beyond the Visible Spectrum Flavio H. D. Araujo1,2,3,4,a, Romuere R. V. Silva1,2,3,4,a, Fatima N. S. Medeiros3,Dilworth D. Parkinson2, Alexander Hexemer2, Claudia M. Carneiro5, Daniela M. Ushizima1,2,* Abstract The explosion in the rate, quality and diversity of image acquisition instruments has propelled the development of expert systems to organize and query image collections more efficiently. Recommendation systems that handle scientific images are rare, particularly if records lack metadata. This paper introduces new strategies to enable fast searches and image ranking from large pictorial datasets with or without labels. The main contribution is the development of pyCBIR, a deep neural network software to search scientific images by content. This tool exploits convolutional layers with locality sensitivity hashing for querying images across domains through a user-friendly interface. Our results report image searches over databases ranging from thousands to millions of samples. We test pyCBIR search capabilities using three convNets against four scientific datasets, including samples from cell microscopy, microtomography, atomic diffraction patterns, and materials photographs to demonstrate 95% accurate recommendations in most cases. Furthermore, all scientific data collections are released. Keywords Reverse image search — Content-based image retrieval — Scientific image recommendation — Convolutional neural network 1University of California, Berkeley, CA, USA 2Lawrence Berkeley National Laboratory, Berkeley, CA, USA 3Federal University of Ceara,´ Fortaleza, CE, Brazil 4Federal University of Piau´ı, Picos, PI, Brazil 5Federal University of Ouro Preto, Ouro Preto, MG, Brazil *Corresponding author: [email protected] aContributed equally to this work.
    [Show full text]
  • Generative Adversarial Transformers
    Generative Adversarial Transformers Drew A. Hudsonx 1 C. Lawrence Zitnick 2 Abstract We introduce the GANsformer, a novel and effi- cient type of transformer, and explore it for the task of visual generative modeling. The network employs a bipartite structure that enables long- range interactions across the image, while main- taining computation of linear efficiency, that can readily scale to high-resolution synthesis. It itera- tively propagates information from a set of latent variables to the evolving visual features and vice versa, to support the refinement of each in light of the other and encourage the emergence of compo- sitional representations of objects and scenes. In contrast to the classic transformer architecture, it utilizes multiplicative integration that allows flexi- Figure 1. Sample images generated by the GANsformer, along ble region-based modulation, and can thus be seen with a visualization of the model attention maps. as a generalization of the successful StyleGAN network. We demonstrate the model’s strength and prior knowledge inform the interpretation of the par- and robustness through a careful evaluation over ticular (Gregory, 1970). While their respective roles and a range of datasets, from simulated multi-object dynamics are being actively studied, researchers agree that it environments to rich real-world indoor and out- is the interplay between these two complementary processes door scenes, showing it achieves state-of-the- that enables the formation of our rich internal representa- art results in terms of image quality and diver- tions, allowing us to perceive the world in its fullest and sity, while enjoying fast learning and better data- create vivid imageries in our mind’s eye (Intaite˙ et al., 2013).
    [Show full text]
  • Neural Network FAQ, Part 1 of 7
    Neural Network FAQ, part 1 of 7: Introduction Archive-name: ai-faq/neural-nets/part1 Last-modified: 2002-05-17 URL: ftp://ftp.sas.com/pub/neural/FAQ.html Maintainer: [email protected] (Warren S. Sarle) Copyright 1997, 1998, 1999, 2000, 2001, 2002 by Warren S. Sarle, Cary, NC, USA. --------------------------------------------------------------- Additions, corrections, or improvements are always welcome. Anybody who is willing to contribute any information, please email me; if it is relevant, I will incorporate it. The monthly posting departs around the 28th of every month. --------------------------------------------------------------- This is the first of seven parts of a monthly posting to the Usenet newsgroup comp.ai.neural-nets (as well as comp.answers and news.answers, where it should be findable at any time). Its purpose is to provide basic information for individuals who are new to the field of neural networks or who are just beginning to read this group. It will help to avoid lengthy discussion of questions that often arise for beginners. SO, PLEASE, SEARCH THIS POSTING FIRST IF YOU HAVE A QUESTION and DON'T POST ANSWERS TO FAQs: POINT THE ASKER TO THIS POSTING The latest version of the FAQ is available as a hypertext document, readable by any WWW (World Wide Web) browser such as Netscape, under the URL: ftp://ftp.sas.com/pub/neural/FAQ.html. If you are reading the version of the FAQ posted in comp.ai.neural-nets, be sure to view it with a monospace font such as Courier. If you view it with a proportional font, tables and formulas will be mangled.
    [Show full text]
  • Adversarial Examples in the Physical World
    Workshop track - ICLR 2017 ADVERSARIAL EXAMPLES IN THE PHYSICAL WORLD Alexey Kurakin Ian J. Goodfellow Samy Bengio Google Brain OpenAI Google Brain [email protected] [email protected] [email protected] ABSTRACT Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been mod- ified very slightly in a way that is intended to cause a machine learning classifier to misclassify it. In many cases, these modifications can be so subtle that a human observer does not even notice the modification at all, yet the classifier still makes a mistake. Adversarial examples pose security concerns because they could be used to perform an attack on machine learning systems, even if the adversary has no access to the underlying model. Up to now, all previous work has assumed a threat model in which the adversary can feed data directly into the machine learn- ing classifier. This is not always the case for systems operating in the physical world, for example those which are using signals from cameras and other sensors as input. This paper shows that even in such physical world scenarios, machine learning systems are vulnerable to adversarial examples. We demonstrate this by feeding adversarial images obtained from a cell-phone camera to an ImageNet In- ception classifier and measuring the classification accuracy of the system. We find that a large fraction of adversarial examples are classified incorrectly even when perceived through the camera. 1 INTRODUCTION (a) Image from dataset (b) Clean image (c) Adv. image, = 4 (d) Adv.
    [Show full text]
  • From Digital Computing to Brain-Like Neuromorphic Accelerator
    Mahyar SHAHSAVARI Lille University of Science and Technology Doctoral Thesis Unconventional Computing Using Memristive Nanodevices: From Digital Computing to Brain-like Neuromorphic Accelerator Supervisor: Pierre BOULET Thèse en vue de l’obtention du titre de Docteur en INFORMATIQUE DE L’UNIVERSITÉ DE LILLE École Doctorale des Sciences Pour l’Ingénieur de Lille - Nord De France 14-Dec-2016 Jury: Hélène Paugam-Moisy Professor of University of the French West Indies (Université des Antilles), France (Rapporteur) Michel Paindavoine Professor of University of Burgundy (Université de Bourgogne), France (Rapporteur) Virginie Hoel Professor of Lille University of Science and Technology, France(Président) Said Hamdioui Professor of Delft University of Technology, The Netherlands Pierre Boulet Professor of Lille University of Science and Technology, France Acknowledgment Firstly, I would like to express my sincere gratitude to my advisor Prof. Pierre Boulet for all kind of supports during my PhD. I never forget his supports specially during the last step of my PhD that I was very busy due to teaching duties. Pierre was really punctual and during three years of different meetings and discussions, he was always available on time and as a record he never canceled any meeting. I learned a lot form you Pierre, specially the way of writing, communicating and presenting. you were an ideal supervisor for me. Secondly, I am grateful of my co-supervisor Dr Philippe Devienne. As I did not knew any French at the beginning of my study, it was not that easy to settle down and with Philippe supports the life was more comfortable and enjoyable for me and my family here in Lille.
    [Show full text]
  • Unconventional Computing Using Memristive Nanodevices: from Digital Computing to Brain-Like Neuromorphic Accelerator
    Mahyar SHAHSAVARI Lille University of Science and Technology Doctoral Thesis Unconventional Computing Using Memristive Nanodevices: From Digital Computing to Brain-like Neuromorphic Accelerator Supervisor: Pierre BOULET Thèse en vue de l’obtention du titre de Docteur en INFORMATIQUE DE L’UNIVERSITÉ DE LILLE École Doctorale des Sciences Pour l’Ingénieur de Lille - Nord De France 14-Dec-2016 Jury: Hélène Paugam-Moisy Professor of University of the French West Indies (Université des Antilles), France (Rapporteur) Michel Paindavoine Professor of University of Burgundy (Université de Bourgogne), France (Rapporteur) Virginie Hoel Professor of Lille University of Science and Technology, France(Président) Said Hamdioui Professor of Delft University of Technology, The Netherlands Pierre Boulet Professor of Lille University of Science and Technology, France Acknowledgment Firstly, I would like to express my sincere gratitude to my advisor Prof. Pierre Boulet for all kind of supports during my PhD. I never forget his supports specially during the last step of my PhD that I was very busy due to teaching duties. Pierre was really punctual and during three years of different meetings and discussions, he was always available on time and as a record he never canceled any meeting. I learned a lot form you Pierre, specially the way of writing, communicating and presenting. you were an ideal supervisor for me. Secondly, I am grateful of my co-supervisor Dr Philippe Devienne. As I did not knew any French at the beginning of my study, it was not that easy to settle down and with Philippe supports the life was more comfortable and enjoyable for me and my family here in Lille.
    [Show full text]
  • Arxiv:1611.08903V1 [Cs.LG] 27 Nov 2016 20 Percent Increases in Cash Collections [20]
    Should I use TensorFlow? An evaluation of TensorFlow and its potential to replace pure Python implementations in Machine Learning Martin Schrimpf1;2;3 1 Augsburg University 2 Technische Universit¨atM¨unchen 3 Ludwig-Maximilians-Universit¨atM¨unchen Seminar \Human-Machine Interaction and Machine Learning" Supervisor: Elisabeth Andr´e Advisor: Dominik Schiller Abstract. Google's Machine Learning framework TensorFlow was open- sourced in November 2015 [1] and has since built a growing community around it. TensorFlow is supposed to be flexible for research purposes while also allowing its models to be deployed productively [7]. This work is aimed towards people with experience in Machine Learning consider- ing whether they should use TensorFlow in their environment. Several aspects of the framework important for such a decision are examined, such as the heterogenity, extensibility and its computation graph. A pure Python implementation of linear classification is compared with an im- plementation utilizing TensorFlow. I also contrast TensorFlow to other popular frameworks with respect to modeling capability, deployment and performance and give a brief description of the current adaption of the framework. 1 Introduction The rapidly growing field of Machine Learning has been gaining more and more attention, both in academia and in businesses that have realized the added value. For instance, according to a McKinsey report, more than a dozen European banks switched from statistical-modeling approaches to Machine Learning tech- niques and, in some cases, increased their sales of new products by 10 percent and arXiv:1611.08903v1 [cs.LG] 27 Nov 2016 20 percent increases in cash collections [20]. Intelligent machines are used in a variety of domains, including writing news articles [5], finding promising recruits given their CV [9] and many more.
    [Show full text]
  • Neural Network FAQ, Part 1 of 7: Introduction
    Neural Network FAQ, part 1 of 7: Introduction Archive-name: ai-faq/neural-nets/part1 Last-modified: 2002-05-17 URL: ftp://ftp.sas.com/pub/neural/FAQ.html Maintainer: [email protected] (Warren S. Sarle) Copyright 1997, 1998, 1999, 2000, 2001, 2002 by Warren S. Sarle, Cary, NC, USA. --------------------------------------------------------------- Additions, corrections, or improvements are always welcome. Anybody who is willing to contribute any information, please email me; if it is relevant, I will incorporate it. The monthly posting departs around the 28th of every month. --------------------------------------------------------------- This is the first of seven parts of a monthly posting to the Usenet newsgroup comp.ai.neural-nets (as well as comp.answers and news.answers, where it should be findable at any time). Its purpose is to provide basic information for individuals who are new to the field of neural networks or who are just beginning to read this group. It will help to avoid lengthy discussion of questions that often arise for beginners. SO, PLEASE, SEARCH THIS POSTING FIRST IF YOU HAVE A QUESTION and DON'T POST ANSWERS TO FAQs: POINT THE ASKER TO THIS POSTING The latest version of the FAQ is available as a hypertext document, readable by any WWW (World Wide Web) browser such as Netscape, under the URL: ftp://ftp.sas.com/pub/neural/FAQ.html. If you are reading the version of the FAQ posted in comp.ai.neural-nets, be sure to view it with a monospace font such as Courier. If you view it with a proportional font, tables and formulas will be mangled.
    [Show full text]
  • Submission Data for 2020-2021 CORE Conference Ranking Process International Conference on Learning Representations
    Submission Data for 2020-2021 CORE conference Ranking process International Conference on Learning Representations Alexander Rush, Hugo LaRochelle Conference Details Conference Title: International Conference on Learning Representations Acronym : ICLR Requested Rank Rank: A* Primarily CS Is this conference primarily a CS venue: True Location Not commonly held within a single country, set of countries, or region. DBLP Link DBLP url: https://dblp.uni-trier.de/db/conf/iclr/index.html FoR Codes For1: 4611 For2: SELECT For3: SELECT Recent Years Proceedings Publishing Style Proceedings Publishing: self-contained Link to most recent proceedings: https://openreview.net/group?id=ICLR.cc/2020/Conference Further details: We don’t have a publisher. Instead we host our publications on OpenReview Most Recent Years Most Recent Year Year: 2019 URL: https://iclr.cc/Conferences/2019 Location: New Orleans, Louisiana, USA Papers submitted: 1591 Papers published: 500 Acceptance rate: 31 Source for numbers: https://github.com/lixin4ever/Conference-Acceptance-Rate General Chairs 1 Name: Tara Sainath Affiliation: Google Gender: F H Index: 50 GScholar url: https://scholar.google.com/citations?hl=en&user=aMeteU4AAAAJ DBLP url: https://dblp.org/pid/28/7825.html Program Chairs Name: Alexander Rush Affiliation: Cornell University Gender: M H Index: 34 GScholar url: https://scholar.google.com/citations?user=LIjnUGgAAAAJ&hl=en&oi=ao DBLP url: https://dblp.org/pid/67/9012.html Name: Sergey Levine Affiliation: University of California Berkeley, Google Gender: M H Index: 84
    [Show full text]