Recent Advances in Big Data and Deep Learning Proceedings of the INNS Big Data and Deep Learning Conference INNSBDDL2019, Held at Sestri Levante, Genova, Italy 16-18 April 2019 /: Proceedings of the INNS Big Data and Deep Learning Conference INNSBDDL2019, Held at Sestri Levante, Genova, Italy 16-18 April 2019. (c2020)

• Record Type: Book
• Further Information: Note: Luca Oneto, Nicolò Navarin, Alessandro Sperduti, Davide Anguita, editors.
• Other Names: Oneto, Luca; Navarin, Nicolò; Sperduti, A (Alessandro); Anguita, Davide; INNSBDDL (Conference)
• Contents: Intro; Preface; Contents; On the Trade-Off Between Number of Examples and Precision of Supervision in Regression; 1 Introduction; 2 Model; 3 Optimal Trade-Off Between Number of Examples and Precision of Supervision Under Ordinary Least Squares; 4 Extensions; References; Distributed SmSVM Ensemble Learning; 1 Introduction; 2 Background; 3 Related Work; 3.1 Hadoop and Spark; 3.2 Message Passing-Based Approaches; 4 Distributed Ensemble SmSVM; 5 Discussion; 5.1 Results; 6 Conclusion; References; Size/Accuracy Trade-Off in Convolutional Neural Networks: An Evolutionary Approach; 1 Introduction 2 Literature Review2.1 NeuroEvolution/Grammar-Based Approaches; 2.2 Size/Accuracy Trade-Off in ANNs; 3 Experimental Setup; 4 Results; 5 Discussion; 5.1 Experiment 1; 5.2 Experiment 2; 6 Conclusions and Future Work; References; Fast Transfer Learning for Image Polarity Detection; 1 Introduction; 2 Image Polarity Detection with Deep Learning; 2.1 CNNs for Object Recognition; 2.2 Image Polarity Detection with CNNs: State of the Art; 3 A Compared Analysis; 3.1 Image Polarity Detector: The Design; 3.2 Computational Complexity; 4 Experimental Results; 4.1 Experimental Setup 4.2 Results and CommentsReferences; Dropout for Recurrent Neural Networks; 1 Introduction; 2 Literature Review; 3 Benchmarks; 3.1 Bouncing Ball Benchmark; 3.2 Language Modelling Benchmark; 4 Experimental Procedure; 5 Results and Discussion; 6 Conclusion; References; Psychiatric Disorders Classification with 3D Convolutional Neural Networks; 1 Introduction; 2 Background and Related Work; 2.1 Related Work; 3 Experimental Assessment; 3.1 Datasets Description; 3.2 Baselines and Neural Architectures; 3.3 Preprocessing Pipeline; 3.4 Evaluation; 4 Conclusions; References Perturbed Proximal Descent to Escape Saddle Points for Non-convex and Non-smooth Objective Functions1 Introduction; 1.1 Related Literature; 2 Algorithm; 3 Escaping Saddle Points Through Perturbed Proximal Descent; 3.1 Lemma: Iterates Remain Bounded if Stuck Near a Saddle Point; 3.2 Preparation for Building Pillars; 3.3 Lemma: Perturbed Iterates Will Escape the Saddle Point; 3.4 Combining Previous Results; 3.5 Main Lemma; 3.6 Main Theorem, and Its Proof; 3.7 From -Second-Order Stationary Point to Local Minimizers; 4 Numerical Experiment; 4.1 Results; 5 Conclusion; References Deep-Learning Domain Adaptation Techniques for Credit Cards Fraud Detection1 Introduction; 2 Background and Notation; 3 Related Work; 4 Transfer Learning Strategies for Fraud Detection; 5 Experimental Comparisons; 6 Discussion; 7 Conclusion; References; Selective Information Extraction Strategies for Cancer Pathology Reports with Convolutional Neural Networks; 1 Introduction; 2 Methods; 2.1 Cancer Pathology Data Corpus; 2.2 Convolutional Neural Networks for Natural Text Data; 2.3 Selective Classification Strategies; 2.4 10-Fold Cross-Validation Study of the Novelty Detection Algorithm
• Publisher Details: Cham : Springer
• Publication Date: 2020
• Copyright Date: 2020
• Extent: 1 online resource (402 p.)
• Subjects: 005.7; Big data -- Congresses; Machine learning -- Congresses; Electronic books
• Languages: English
• ISBNs: 9783030168414; 3030168417
• Related ISBNs: 9783030168407
• Access Rights: Legal Deposit; Only available on premises controlled by the deposit library and to one user at any one time; The Legal Deposit Libraries (Non-Print Works) Regulations (UK).
• Access Usage: Restricted: Printing from this resource is governed by The Legal Deposit Libraries (Non-Print Works) Regulations (UK) and UK copyright law currently in force.