Filters








2,120 Hits in 5.1 sec

HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning [article]

Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui, Satoshi Sekine, Lasha Abzianidze, Johan Bos
2019 arXiv   pre-print
Since no large dataset has been developed for monotonicity reasoning, it is still unclear whether the main obstacle is the size of datasets or the model architectures themselves.  ...  We add it to training data for the state-of-the-art neural models and evaluate them on test sets for monotonicity phenomena.  ...  Acknowledgement We thank our three anonymous reviewers for helpful suggestions.  ... 
arXiv:1904.12166v1 fatcat:cqu5c55qxrg5jdsejz3xsfijfm

HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning

Hitomi Yanaka, Koji Mineshima, Daisuke Bekki, Kentaro Inui, Satoshi Sekine, Lasha Abzianidze, Johan Bos
2019 Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)  
Since no large dataset has been developed for monotonicity reasoning, it is still unclear whether the main obstacle is the size of datasets or the model architectures themselves.  ...  We add it to training data for the state-of-the-art neural models and evaluate them on test sets for monotonicity phenomena.  ...  Acknowledgement We thank our three anonymous reviewers for helpful suggestions.  ... 
doi:10.18653/v1/s19-1027 dblp:conf/starsem/YanakaMBISAB19 fatcat:nitpb4ca2bgh3eomzp4ks6szma

Decomposing Natural Logic Inferences in Neural NLI [article]

Julia Rozanova, Deborah Ferreira, Marco Valentino, Mokanrarangan Thayaparan, Andre Freitas
2021 arXiv   pre-print
In the interest of interpreting neural NLI models and their reasoning strategies, we carry out a systematic probing study which investigates whether these models capture the crucial semantic features central  ...  Correctly identifying valid inferences in downward-monotone contexts is a known stumbling block for NLI performance, subsuming linguistic phenomena such as negation scope and generalized quantifiers.  ...  The shortcomings of natural logic handling in various neural NLI models have been shown with several behavioural studies, where NLI challenge sets exhibiting examples of downward monotone reasoning are  ... 
arXiv:2112.08289v1 fatcat:zcrhzaaxcze6hgqkigq7vrgsje

MonoNet: Towards Interpretable Models by Learning Monotonic Features [article]

An-phi Nguyen, María Rodríguez Martínez
2019 arXiv   pre-print
We argue that by enforcing monotonicity between features and outputs, we are able to reason about the effect of a single feature on an output independently from other features, and consequently better  ...  called for a more active conversation towards a rigorous approach to interpretability.  ...  This is needed for Goal 1. Expressiveness In order to identify biases in a dataset or in other models (Goal 2), the interpretable model should be unbiased, i.e. an universal approximator.  ... 
arXiv:1909.13611v1 fatcat:w5jgookpardlflw5r2c4hqsuli

With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization [article]

James Wang, Cheng-Lin Yang
2022 arXiv   pre-print
Generalization of deep neural networks remains one of the main open problems in machine learning.  ...  In this paper, we empirically examined how different layers of neural networks contribute differently to the model; we found that early layers generally learn representations relevant to performance on  ...  For fully connected neural networks without skip layers, the contribution of neural networks layers follows a monotonic pattern, where early layers (closer to input) start taking effect early on, and deeper  ... 
arXiv:2201.11939v1 fatcat:pwmlbhb2ubaihelkdzwlnmzsj4

Periodic Spectral Ergodicity: A Complexity Measure for Deep Neural Networks and Neural Architecture Search [article]

Mehmet Süzen, J.J. Cerdà, Cornelius Weber
2020 arXiv   pre-print
We demonstrate the usefulness of this measure in practice on two sets of vision models, ResNet and VGG, and sketch the computation of cPSE for more complex network structures.  ...  Because of this cascading approach, i.e., a symmetric divergence of PSE on the consecutive layers, it is possible to use this measure for Neural Architecture Search (NAS).  ...  these datasets neatly.  ... 
arXiv:1911.07831v4 fatcat:nh6lfc6lcbfmpfv5tqoctepnvi

A neural network filtering approach for similarity-based remaining useful life estimation

Oguz Bektas, Jeffrey A. Jones, Shankar Sankararaman, Indranil Roychoudhury, Kai Goebel
2018 The International Journal of Advanced Manufacturing Technology  
The framework proposed in this paper considers a similarity-based prognostic algorithm that is fed by the use of data normalisation and filtering methods for operational trajectories of complex systems  ...  This is combined with a data-driven prognostic technique based on feed-forward neural networks with multi-regime normalisation.  ...  The main reason for selection of this fitting approach is that the fitted HIs, y, for training trajectories have only increasing values and early stages are behaving in such a way that the fitting has  ... 
doi:10.1007/s00170-018-2874-0 fatcat:adgkgaydmvcknprlhbdcoc3xku

Statistics and data mining techniques for lifetime value modeling

D. R. Mani, James Drew, Andrew Betz, Piew Datta
1999 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '99  
many of the shortcomings of each separate tool setresulting in a LTV tenure prediction model that is both accurate and understandable.  ...  A new neural network model for hazard prediction is used to free proportional hazards-like models from their linearity and proportionality constraints, and clustering tools are applied to identify segments  ...  . large datasets over a large number of time intervals, where the models need to be refreshed frequently with reasonable turn around times in a corporate setting.  ... 
doi:10.1145/312129.312205 dblp:conf/kdd/ManiDBD99 fatcat:lwzgmipuo5ccfk5ish3dsbgw2m

Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation [article]

Chaochao Lu, Biwei Huang, Ke Wang, José Miguel Hernández-Lobato, Kun Zhang, Bernhard Schölkopf
2020 arXiv   pre-print
Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment.  ...  To address the issues of mechanism heterogeneity and related data scarcity, we propose a data-efficient RL algorithm that exploits structural causal models (SCMs) to model the state dynamics, which are  ...  , we achieve flexible counterfactual reasoning in the general case, by adopting neural networks for function approximation of the SCM with no hard restrictions on data distribution or causal mechanisms  ... 
arXiv:2012.09092v1 fatcat:ejv3zbxnibcerkwyidm6i2l2xa

A frgsnn hybrid feature selection combining frgs filter and gsnn wrapper

Bichitrananda` Patra
2016 International Journal of Latest Trends in Engineering and Technology  
How to selecting a small subset out of the thousands of genes in microarray data is important for accurate classification of phenotypes.  ...  of the two specified models for gene selection.  ...  For this reason, a mutation operator capable of spontaneously generating new chromosomes is included.  ... 
doi:10.21172/1.72.502 fatcat:anidioanyzctrajskojj2tltni

Cardiac Phase Detection in Echocardiograms With Densely Gated Recurrent Neural Networks and Global Extrema Loss

Fatemeh Taheri Dezaki, Zhibin Liao, Christina Luong, Hany Girgis, Neeraj Dhungel, Amir H. Abdi, Delaram Behnami, Ken Gin, Robert Rohling, Purang Abolmaesumi, Teresa Tsang
2019 IEEE Transactions on Medical Imaging  
The proposed architectures integrate convolution neural networks (CNNs)-based image feature extraction model and recurrent neural networks (RNNs) to model temporal dependencies between each frame in a  ...  The optimal deep learning model consists of a DenseNet and GRU trained with the proposed loss function.  ...  ACKNOWLEDGMENT The authors would like to thank Dale Hawley for helping with accessing data used in this research.  ... 
doi:10.1109/tmi.2018.2888807 pmid:30582532 fatcat:yssmwjupkrdvbjlyd2gh74l5ju

Effective Sparsification of Neural Networks with Global Sparsity Constraint [article]

Xiao Zhou, Weizhong Zhang, Hang Xu, Tong Zhang
2021 arXiv   pre-print
Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments.  ...  As a by-product, we show ProbMask is also highly effective in identifying supermasks, which are subnetworks with high performance in a randomly weighted dense neural network.  ...  ProbMask can also serve as a powerful tool for identifying subnetworks with high performance in a randomly weighted dense neural network. A.  ... 
arXiv:2105.01571v1 fatcat:mdhmrmlyerbahmqgf2ju3mjyqu

Pushing the Limits of Low-Resource Morphological Inflection [article]

Antonios Anastasopoulos, Graham Neubig
2019 arXiv   pre-print
However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art neural methods that work well under higher resource settings perform poorly in the face of a paucity  ...  Also, we identify the crucial factors for success with cross-lingual transfer for morphological inflection: typological similarity and a common representation across languages.  ...  as to Gabriela Weigel for her invaluable help with editing and proofreading the paper.  ... 
arXiv:1908.05838v2 fatcat:ahvfqej45ngadixgkje46fzxra

Interpretable machine learning: Fundamental principles and 10 grand challenges

Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, Chudi Zhong
2022 Statistics Survey  
better interpretability; (4) Modern case-based reasoning, including neural networks and matching for causal inference; (5) Complete supervised disentanglement of neural networks; (6) Complete or even partial  ...  This survey is suitable as a starting point for statisticians and computer scientists interested in working in interpretable machine learning.  ...  Thank you to the anonymous reviewers that made extremely helpful comments.  ... 
doi:10.1214/21-ss133 fatcat:ahzfoilhmfa2rd4hcauvsn3eyy

Capturing and incorporating expert knowledge into machine learning models for quality prediction in manufacturing [article]

Patrick Link, Miltiadis Poursanidis, Jochen Schmid, Rebekka Zache, Martin von Kurnatowski, Uwe Teicher, Steffen Ihlenfeldt
2022 arXiv   pre-print
In particular, the direct involvement of process experts in the training of the models leads to a very clear interpretation and, by extension, to a high acceptance of the models.  ...  In manufacturing, the size of available datasets before start of production is often limited. In contrast to data, expert knowledge commonly is available in manufacturing.  ...  Acknowledgments We gratefully acknowledge the funding provided by the Fraunhofer Society as part of the lighthouse project "Machine Learning for Production" (ML4P).  ... 
arXiv:2202.02003v1 fatcat:vhsjy5a75vewjg23nypz6o2mti
« Previous Showing results 1 — 15 out of 2,120 results