Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

The PASCAL Visual Object Classes Challenge

We explore the effect of dimensionality on the nearest neighbor problem. We show that under a broad set of conditions (much broader than independent and identically distributed dimensions), as dimensionality increases, the distance to the nearest data point approaches the distance to the farthest data point. To provide a practical perspective, we present empirical results on both real and synthetic data sets that demonstrate that this effect can occur for as few as 10-15 dimensions. These results should not be interpreted to mean that high-dimensional indexing is never meaningful; we illustrate this point by identifying some high-dimensional workloads for which this effect does not occur. However, our results do emphasize that the methodology used almost universally in the database literature to evaluate high-dimensional indexing techniques is flawed, and should be modified. In particular, most such techniques proposed in the literature are not evaluated versus simple linear scan, and are evaluated over workloads for which nearest neighbor is not meaningful. Often, even the reported experiments, when analyzed carefully, show that linear scan would outperform the techniques being proposed on the workloads studied in high (10-15) dimensionality!.

When is nearest neighbor meaningful

A systematic study of the class imbalance problem in convolutional neural networks

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

This paper presents a deep learning approach for image retrieval and pattern spotting in digital collections of historical documents. First, a region proposal algorithm detects object candidates in the document page images. Next, deep learning models are used for feature extraction, considering two distinct variants, which provide either real-valued or binary code representations. Finally, candidate images are ranked by computing the feature similarity with a given input query. A robust experimental protocol evaluates the proposed approach considering each representation scheme (real-valued and binary code) on the DocExplore image database. The experimental results show that the proposed deep models compare favorably to the state-of-the-art image retrieval approaches for images of historical documents, outperforming other deep models by 2.56 percentage points using the same techniques for pattern spotting. Besides, the proposed approach also reduces the search time up to 200$\times$, and the storage cost up to 6,000$\times$ when compared to related works based on real-valued representations.

Pattern Spotting and Image Retrieval in Historical Documents using Deep Hashing

Dans cet article, nous proposons une methode d'optimisation multi-objectif pour la selection de modele SVM, en utilisant l'algorithme NSGA-II. Le faux rejet et la fausse acceptation sont les deux criteres employes pour trouver les hyperparameters optimaux d'un ensemble de classifieurs SVM. La strategie proposee est appliquee a une tâche de discrimination chiffre/rejet embarquee dans un systeme plus global d'extraction d'information dans des documents manuscrits. Nos experimentations sur une base reelle de chiffres/rejet montrent que notre methode fournit de meilleurs resultats que les techniques d'optimisation mono-objectif plus classiques telle que l'apprentissage base sour un critere d'aire sous la courbe ROC. Ces resultats sont dans un second temps valides sur des bases de l'UCI.

https://hal.archives-ouvertes.fr/hal-00671129/document

Optimisation multi-objectif pour la sélection de modèles SVM

In this paper, we present our recent work on the Bovary project, a manuscript digitization project of the famous French writer Gustave Flaubert, which aims at providing an online access to a hyper textual edition of “Madame Bovary” draft sets. We first describe the global context of this project, its main objectives, and then focus on the document image analysis problem for which we have developed effective and powerful page layout extraction algorithms based on markovian generative and discriminative models such as Hidden Markov Random Fields and Conditional Random Fields. We show with some experiments that these stochastic and contextual models are able to cope with local spatial variability while taking into account some prior knowledge about the global structure of the document image, thus being well suited to the segmentation of very complex document images like authorial manuscripts or historical documents.

Authorial manuscript image analysis using markovian models: the Bovary project

Approximating dynamic time warping with a convolutional neural network on EEG data

and key words In this communication we apply an Information Retrieval model for the writer identification task. Queries are handwreitten document images projected on a suitable feature set. The handwritten document database is indexed according to the vector space model originaly used for textual information. The approach uses both the image and textual description of handwritten documents. Identified documents are then processed by the verification stage. We use a mutual information criterion so as to verify that each identified document can have been written by the writer of the query. Decision operates using an hypothesis test. The approcah is evaluated on two different database and proves to be robust to the variability of handwriting. Perspectives are oriented towards the use of large handwritten document database

http://documents.irevues.inist.fr/bitstream/handle/2042/4395/06%22Bensefia%20et%20al%20couleur.pdf?sequence=1

Laurent Heutte

Papers

Pattern Spotting and Image Retrieval in Historical Documents using Deep Hashing

Optimisation multi-objectif pour la sélection de modèles SVM

Authorial manuscript image analysis using markovian models: the Bovary project

Approximating dynamic time warping with a convolutional neural network on EEG data

Identification et Vérification du Scripteur dans des Documents Manuscrits Writer identification and verification in handwritten documents