Filters








642 Hits in 8.6 sec

Planning in Factored State and Action Spaces with Learned Binarized Neural Network Transition Models

Buser Say, Scott Sanner
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In this paper, we leverage the efficiency of Binarized Neural Networks (BNNs) to learn complex state transition models of planning domains with discretized factored state and action spaces.  ...  Experimentally, we show the effectiveness of learning complex transition models with BNNs, and test the runtime efficiency of both encodings on the learned factored planning problem.  ...  Binarized Neural Networks (BNNs) are neural networks with binary weights and activation functions [Hubara et al., 2016].  ... 
doi:10.24963/ijcai.2018/669 dblp:conf/ijcai/SayS18 fatcat:zosgoamtlzbnlamxqyp2apxfpu

Compact and Efficient Encodings for Planning in Factored State and Action Spaces with Learned Binarized Neural Network Transition Models [article]

Buser Say, Scott Sanner
2020 arXiv   pre-print
In this paper, we leverage the efficiency of Binarized Neural Networks (BNNs) to learn complex state transition models of planning domains with discretized factored state and action spaces.  ...  transition models with BNNs.  ...  As an alternative to ReLU-based DNNs, Binarized Neural Networks (BNNs) [8] have been introduced with the specific ability to learn compact models over discrete variables, providing a new formalism for  ... 
arXiv:1811.10433v12 fatcat:wa4httvsh5brbejmoxmbw77jfq

Asynchronous network of cellular automaton-based neurons for efficient implementation of Boltzmann machines

Takashi Matsubara, Kuniaki Uehara
2018 Nonlinear Theory and Its Applications IEICE  
Artificial neural networks with stochastic state transitions and calculations, such as Boltzmann machines, have excelled over other machine learning approaches in various benchmark tasks.  ...  The networks often achieve better results than deterministic neural networks of similar sizes, but they require implementation of nonlinear continuous functions for probabilistic density functions, thus  ...  Acknowledgments This study was partially supported by the KAKENHI (16K12487), Kayamori Foundation of Information Science Advancement, and The Nakajima Foundation.  ... 
doi:10.1587/nolta.9.24 fatcat:2l42p2kw25b6thujaqcw2wkcbe

Application of Artificial Intelligence Nuclear Medicine Automated Images Based on Deep Learning in Tumor Diagnosis

Jian Sun, Xin Yuan, Bhagyaveni M.A
2022 Journal of Healthcare Engineering  
model based on boundary constraints, and proposes a superpixel boundary-aware convolution network to realize the automatic CT cutting algorithm.  ...  The experimental results in this paper show that the improved algorithm in this paper is more robust than the traditional CT algorithm in terms of accuracy and sensitivity, an increase of about 12%, and  ...  Deep learning is a branch of machine learning algorithms. e essence is a multilayer neural network structure.  ... 
doi:10.1155/2022/7247549 pmid:35140903 pmcid:PMC8820925 fatcat:cnus6hwmrbb7ph2ixho4syug3u

Integrating long-range regulatory interactions to predict gene expression using graph convolutional neural networks [article]

Jeremy Bigness, Xavi Loinaz, Shalin Patel, Erica Larschan, Ritambhara Singh
2020 bioRxiv   pre-print
Here, we propose a graph convolutional neural network (GCNN) framework to integrate measurements probing spatial genomic organization and measurements of local regulatory factors, specifically histone  ...  Long-range spatial interactions among genomic regions are critical for regulating gene expression and their disruption has been associated with a host of diseases.  ...  Acknowledgments We are grateful to members of the COBRE-CBHD Computational Biology Core (CBC) at Brown University for helpful discussions and suggestions.  ... 
doi:10.1101/2020.11.23.394478 fatcat:wlcmq3temjfivid7kgodhbzxx4

A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges [article]

Denis Kleyko, Dmitri A. Rachkovskij, Evgeny Osipov, Abbas Rahimi
2022 arXiv   pre-print
Holographic Reduced Representations is an influential HDC/VSA model that is well-known in the machine learning domain and often used to refer to the whole family.  ...  The survey is written to be useful for both newcomers and practitioners.  ...  Interplay with neural networks HVs as input to neural networks One of the most obvious ways to make an interplay between HDC/VSA and neural networks is by using HVs to represent input to neural networks  ... 
arXiv:2112.15424v2 fatcat:uteoq33hgna2fhs2o46rkde2iq

Deep Learning-Assisted Classification of Site-Resolved Quantum Gas Microscope Images [article]

Lewis R. B. Picard, Manfred J. Mark, Francesca Ferlaino, Rick van Bijnen
2019 arXiv   pre-print
We present a novel method for the analysis of quantum gas microscope images, which uses deep learning to improve the fidelity with which lattice sites can be classified as occupied or unoccupied.  ...  We devise two feedforward neural network architectures which are both able to improve upon the fidelity of threshold-based methods, following training on large data sets of simulated images.  ...  [16, 17, 18] and evaluating theoretical models of interactions of fermions in an optical lattice [19] .  ... 
arXiv:1904.08074v1 fatcat:hdznndhaqzcsho4vxpt6a476tm

Deep-learning-assisted classification of site-resolved quantum gas microscope images

Lewis Russell Bartos Picard, Manfred J. Mark, Francesca Ferlaino, Rick Van-Bijnen
2019 Measurement science and technology  
We present a novel method for the analysis of quantum gas microscope images, which uses deep learning to improve the fidelity with which lattice sites can be classified as occupied or unoccupied.  ...  We devise two neural network architectures which are both able to improve upon the fidelity of threshold-based methods, following training on large data sets of simulated images.  ...  The neural networks presented were trained using the HPC infrastructure LEO of the University of Innsbruck.  ... 
doi:10.1088/1361-6501/ab44d8 fatcat:mdhjgkenbnblzdpwnm4rddu2cq

Verification for Machine Learning, Autonomy, and Neural Networks Survey [article]

Weiming Xiang and Patrick Musau and Ayana A. Wild and Diego Manzanas Lopez and Nathaniel Hamilton and Xiaodong Yang and Joel Rosenfeld and Taylor T. Johnson
2018 arXiv   pre-print
Autonomy in CPS is enabling by recent advances in artificial intelligence (AI) and machine learning (ML) through approaches such as deep neural networks (DNNs), embedded in so-called learning enabled components  ...  Recently, the formal methods and formal verification community has developed methods to characterize behaviors in these LECs with eventual goals of formally verifying specifications for LECs, and this  ...  The general neural network model is discussed along with recurrent and feed-forward neural networks.  ... 
arXiv:1810.01989v1 fatcat:a5ax66lsxbho3fuxuh55ypnm6m

Learning Self-Game-Play Agents for Combinatorial Optimization Problems [article]

Ruiyang Xu, Karl Lieberherr
2019 arXiv   pre-print
The ZG also provides a specially designed neural MCTS. We use a combinatorial planning problem for which the ground-truth policy is efficiently computable to demonstrate that ZG is promising.  ...  Recent progress in reinforcement learning (RL) using self-game-play has shown remarkable performance on several board games (e.g., Chess and Go) as well as video games (e.g., Atari games and Dota2).  ...  Acknowledgements: We would like to thank Tal Puhov for his feedback on our paper.  ... 
arXiv:1903.03674v2 fatcat:a4hkhku42ff63lohosmghdcyze

Vector Space Semantic Parsing: A Framework for Compositional Vector Space Models

Jayant Krishnamurthy, Tom M. Mitchell
2013 Annual Meeting of the Association for Computational Linguistics  
We present vector space semantic parsing (VSSP), a framework for learning compositional models of vector space semantics.  ...  We present experiments using noun-verbnoun and adverb-adjective-noun phrases which demonstrate that VSSP can learn composition operations that RNN (Socher et al., 2011) and MV-RNN (Socher et al., 2012)  ...  We thank Matt Gardner, Justin Betteridge, Brian Murphy, Partha Talukdar, Alona Fyshe and the anonymous reviewers for their helpful comments.  ... 
dblp:conf/acl/KrishnamurthyM13 fatcat:4iama44ad5cotcj7dkdg64gzwe

Effects of Hebbian learning on the dynamics and structure of random networks with inhibitory and excitatory neurons [article]

Benoit Siri , Bruno Cessac
2007 arXiv   pre-print
The aim of the present paper is to study the effects of Hebbian learning in random recurrent neural networks with biological connectivity, i.e. sparse connections and separate populations of excitatory  ...  We show that the application of such Hebbian learning leads to drastic changes in the network dynamics and structure.  ...  While the model studied in the present work is much more compatible with our knowledge of biological neural networks, it is very different from the model studied in [40] .  ... 
arXiv:0706.2602v1 fatcat:h7ei5nyxwveetfxydatqubk4xy

LC: A Flexible, Extensible Open-Source Toolkit for Model Compression

Yerlan Idelbayev, Miguel Á. Carreira-Perpiñán
2021 Proceedings of the 30th ACM International Conference on Information & Knowledge Management  
, which results in a "learning-compression" (LC) algorithm.  ...  model compression will remain a critical need for the foreseeable future.  ...  ACKNOWLEDGMENTS Work partially supported by NSF award IIS-1423515 and by several GPU donations from the NVIDIA Corporation.  ... 
doi:10.1145/3459637.3482005 fatcat:rbmlfdct75fyvm2wv6ts2h4f2a

NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning [article]

Zeming Chen, Qiyue Gao, Lawrence S. Moss
2021 arXiv   pre-print
To merge symbolic and deep learning methods, we propose an inference framework called NeuralLog, which utilizes both a monotonicity-based logical inference engine and a neural network language model for  ...  Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI).  ...  Acknowledgements We thank the anonymous reviewers for their insightful comments. We also thank Dr. Michael Wollowski from Rose-hulman Institute of Technology for his helpful feedback on this paper.  ... 
arXiv:2105.14167v3 fatcat:clpvn6m5hnd6zemyh4k7tsxtwa

26th Annual Computational Neuroscience Meeting (CNS*2017): Part 1

Sue Denham, Panayiota Poirazi, Erik De Schutter, Karl Friston, Ho Ka Chan, Thomas Nowotny, Dongqi Han, Sungho Hong, Sophie Rosay, Tanja Wernle, Alessandro Treves, Sarah Goethals (+90 others)
2017 BMC Neuroscience  
Our preliminary results show that with learning the network is reweighted into a new structure with relatively high levels of SW (Fig. 1A) , but a fully connected pattern.  ...  To study changes in oscillation patterns with learning, we modeled brain processing using a directed random network of phase-coupled oscillators interacting according to the Kuramoto model [1].  ...  Our model also demonstrates that such hierarchical learning and planning can be performed by an unsupervised neural network and therefore hints at a biological implementation.  ... 
doi:10.1186/s12868-017-0370-3 fatcat:qq2cmqlotbg7vpqlqmmcql4u5i
« Previous Showing results 1 — 15 out of 642 results