Filters








109 Hits in 1.5 sec

Pylearn2: a machine learning research library [article]

Ian J. Goodfellow, David Warde-Farley, Pascal Lamblin, Vincent Dumoulin, Mehdi Mirza, Razvan Pascanu, James Bergstra, Frédéric Bastien, Yoshua Bengio
2013 arXiv   pre-print
Pylearn2 is a machine learning research library.  ...  This does not just mean that it is a collection of machine learning algorithms that share a common API; it means that it has been designed for flexibility and extensibility in order to facilitate research  ...  Introduction Pylearn2 is a machine learning research library developed by LISA at Université de Montréal. The goal of the library is to facilitate machine learning research.  ... 
arXiv:1308.4214v1 fatcat:nwsear5oenhullzswvv5p6yzae

A Generation Method of Immunological Memory in Clonal Selection Algorithm by Using Restricted Boltzmann Machines

Shin Kamada, Takumi Ichimura
2015 2015 IEEE International Conference on Systems, Man, and Cybernetics  
To verify the effectiveness of the method, some experiments for classification of the subjective data are executed by using machine learning tools for Deep Learning.  ...  Recently, a high technique of image processing is required to extract the image features in real time.  ...  MACHINE LEARNING TOOL Pylearn2 [10] is one of machine learning tools with libraries for Deep Learning [8] .  ... 
doi:10.1109/smc.2015.465 dblp:conf/smc/KamadaI15 fatcat:2enxktegxzf7fbeszzqdancf3e

Toolkits and Libraries for Deep Learning

Bradley J. Erickson, Panagiotis Korfiatis, Zeynettin Akkus, Timothy Kline, Kenneth Philbrick
2017 Journal of digital imaging  
Deep learning is an important new area of machine learning which encompasses a wide range of neural network architectures designed to complete various tasks.  ...  Whereas traditional machine learning requires determination and calculation of features from which the algorithm learns, deep learning approaches learn the important features as well as the proper weighting  ...  creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a  ... 
doi:10.1007/s10278-017-9965-6 pmid:28315069 pmcid:PMC5537091 fatcat:7obzia6qq5futkdaxq3yyap5z4

Blocks and Fuel: Frameworks for deep learning [article]

Bart van Merriënboer, Dzmitry Bahdanau, Vincent Dumoulin, Dmitriy Serdyuk, David Warde-Farley, Jan Chorowski, Yoshua Bengio
2015 arXiv   pre-print
Fuel provides a standard format for machine learning datasets. It allows the user to easily iterate over large datasets, performing many types of pre-processing on the fly.  ...  Blocks is based on Theano, a linear algebra compiler with CUDA-support.  ...  Acknowledgments The authors would like to acknowledge the support of the following agencies for research funding and computing support: NSERC, Calcul Québec, Compute Canada, the Canada Research Chairs  ... 
arXiv:1506.00619v1 fatcat:xp6wxgav4rcg5pgzityagso63i

A Generic Software Platform for Brain-inspired Cognitive Computing

Koichi Takahashi, Kotone Itaya, Masayoshi Nakamura, Moriyoshi Koizumi, Naoya Arakawa, Masaru Tomita, Hiroshi Yamakawa
2015 Procedia Computer Science  
We have been developing BriCA (Brain-inspired Computing Architecture), the generic software platform that can combine an arbitrary number of machine learning modules to construct higher structures such  ...  http://deeplearning.net/software/pylearn2/ Brain-inspired Computing Architecture Takahashi et al.  ...  Open source generic ML libraries such as Scikit-learn (scikit-learn.org), Theano § § , PyBrain (pybrain.org), PyLearn2 *** , and Weka are available to be embedded in modules.  ... 
doi:10.1016/j.procs.2015.12.185 fatcat:zeea55rrgfhj3dl7k5oy5b3zwi

Toward content-based image retrieval with deep convolutional neural networks

Judah E. S. Sklan, Andrew J. Plassard, Daniel Fabbri, Bennett A. Landman, Barjor Gimi, Robert C. Molthen
2015 Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging  
Recent advances in database capacity, algorithm efficiency, and deep Convolutional Neural Networks (dCNN), a machine learning technique, have enabled great CBIR success for general photographic images.  ...  Quantitative results were disappointing (averaging a true positive rate of only 20%); however, the data suggest that improvements would be possible with more evenly distributed sampling across labels and  ...  This work was conducted in part using the resources of the Advanced Computing Center for Research and Education at Vanderbilt University, Nashville, TN.  ... 
doi:10.1117/12.2081551 pmid:25914507 pmcid:PMC4405657 dblp:conf/mibam/SklanPFL15 fatcat:bhvrjpdizzganbtecckxzyk37i

Automating Marine Mammal Detection in Aerial Images Captured During Wildlife Surveys: A Deep Learning Approach [chapter]

Frederic Maire, Luis Mejias Alvarez, Amanda Hodgson
2015 Lecture Notes in Computer Science  
In this paper, we present an efficient machine learning system for automating the detection of marine species in aerial imagery.  ...  Aerial surveys conducted using manned or unmanned aircraft with customized camera payloads can generate a large number of images.  ...  However, a few low-level functions had to be written using the Theano library [4] on which Pylearn2 is built. We compared two CNN architectures for our application (see Figure 4 ).  ... 
doi:10.1007/978-3-319-26350-2_33 fatcat:ygmup4ve2jbu5c2v6grdgime7q

Analysis of using software packages for imaging in medical diagnostics

V. M. Sineglazov, D. S. Raduchych
2016 Electronics and Control Systems  
Libraries Treano and Torch were investigated.  ...  Library Torch Torch -library for scientific computing with broad support machine learning algorithms.  ...  Theano was developed in the laboratory LISA for supporting the rapid development of machine learning algorithms.  ... 
doi:10.18372/1990-5548.50.11399 fatcat:hnvdogrbijdvpjy75frjgt37m4

A Step Forward Towards Deep Learning

Varshapriya J., Minal Ugale
2017 International Journal of Advanced Research in Computer Science and Software Engineering  
Deep learning is no more just a buzzword but a fast scenario turning reality. The current market is trying to optimize its processes using machine learning and deep learning.  ...  Also, the demand for a machine engineer or a deep learning scientist has increased manifold. With this rate, knowing and applying deep learning would not only remain a skill but a necessity.  ...  MLpython is a library for organizing machine learning research.  ... 
doi:10.23956/ijarcsse/v7i3/0121 fatcat:kkww74cx4ffmjltcyqcqx4rrlq

A powerful comparison of deep learning frameworks for Arabic sentiment analysis

Youssra Zahidi, Yacine El Younoussi, Yassine Al-Amrani
2021 International Journal of Power Electronics and Drive Systems (IJPEDS)  
Deep learning (DL) is a machine learning (ML) subdomain that involves algorithms taken from the brain function named artificial neural networks (ANNs).  ...  For working on Arabic SA, researchers can use various DL libraries in their projects, but without justifying their choice or they choose a group of libraries relying on their particular programming language  ...  There is a set of machine learning models powering natural language processing (NLP) applications. Recently, DL approaches have gained high performance across various NLP tasks [3] .  ... 
doi:10.11591/ijece.v11i1.pp745-752 fatcat:jmavlc5bdvcq3glvovciwlbitq

The State of the Art when using GPUs in Devising Image Generation Methods Using Deep Learning [article]

Yasuko Kawahata
2021 arXiv   pre-print
Deep learning is a technique for machine learning using multi-layer neural networks.  ...  About Deep Learning(2015~2016) Deep learning is a technique for machine learning using multilayer neural networks.  ...  It is also highly versatile in that it can be used with cuDNN, a GPU library for deep learning developed by NIVIDIA.  ... 
arXiv:2109.05783v1 fatcat:thrmmglypjampc23jy2y6qpsre

Musical Audio Synthesis Using Autoencoding Neural Nets

Andy M. Sarroff, Michael Casey
2014 Proceedings of the SMC Conferences  
Our models are trained using the Pylearn2 machine learning library [11] which wraps around Theano [12] for fast evaluation of mathematical expressions.  ...  As with any machine learning paradigm, there are also tradeoffs. The ANN is a highly general model and it may be designed in a number of ways.  ... 
doi:10.5281/zenodo.850877 fatcat:7fc5juwmdrd2ffb74ua3e64evq

Mining Big Data Using Modified Induction Tree Approach

Chintan Bhatt, C Bhensdadia
2016 International Journal of Intelligent Engineering and Systems  
The most effective method to separate significant data from huge information has been a famous open issue. In this paper, we are proposing new algorithm of decision tree in big data.  ...  It is an interactive algorithm which is learning at different level of abstractions. Pylearn2: It is a user friendly machine learning library [11] , built on top of Theano.  ...  It is a research library (who provides flexibility and extensibility) developed by LISA lab.  ... 
doi:10.22266/ijies2016.0630.03 fatcat:4zhmb4aqtffndobb6mbvu5zbbm

Caffe

Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, Trevor Darrell
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models.  ...  The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying generalpurpose convolutional neural networks and other deep models efficiently on commodity architectures  ...  As such, it's an ideal starting point for researchers and other developers looking to jump into state-of-the-art machine learning.  ... 
doi:10.1145/2647868.2654889 dblp:conf/mm/JiaSDKLGGD14 fatcat:f43ch33ekjel3mbb2ll3n7svsa

Human activity recognition with smartphone sensors using deep learning neural networks

Charissa Ann Ronao, Sung-Bae Cho
2016 Expert systems with applications  
A wider time span of temporal local correlation can be exploited (1 × 9-1 × 14) and a low pooling size (1 × 2-1 × 3) is shown to be beneficial.  ...  Human activity recognition (HAR), a field that has garnered a lot of attention in recent years due to its high demand in various application domains, makes use of time-series sensor data to infer activities  ...  Next in line is Pylearn2-a rapidly developing machine learning library in Python ( Goodfellow et al., 2013 ) .  ... 
doi:10.1016/j.eswa.2016.04.032 fatcat:ewrocoxmwje3zfejbazinqkhue
« Previous Showing results 1 — 15 out of 109 results