Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Part I. Experimental Studies: 2. Experiment in psychology 3. Experiments on perceiving III Experiments on imaging 4-8. Experiments on remembering: (a) The method of description (b) The method of repeated reproduction (c) The method of picture writing (d) The method of serial reproduction (e) The method of serial reproduction picture material 9. Perceiving, recognizing, remembering 10. A theory of remembering 11. Images and their functions 12. Meaning Part II. Remembering as a Study in Social Psychology: 13. Social psychology 14. Social psychology and the matter of recall 15. Social psychology and the manner of recall 16. Conventionalism 17. The notion of a collective unconscious 18. The basis of social recall 19. A summary and some conclusions.

Remembering. A Study in Experimental and Social Psychology, Cambridge (University Press) 1964.

The European Position Paper on Rhinosinusitis and Nasal Polyps 2020 is the update of similar evidence based position papers published in 2005 and 2007 and 2012. The core objective of the EPOS2020 guideline is to provide revised, up-to-date and clear evidence-based recommendations and integrated care pathways in ARS and CRS. EPOS2020 provides an update on the literature published and studies undertaken in the eight years since the EPOS2012 position paper was published and addresses areas not extensively covered in EPOS2012 such as paediatric CRS and sinus surgery. EPOS2020 also involves new stakeholders, including pharmacists and patients, and addresses new target users who have become more involved in the management and treatment of rhinosinusitis since the publication of the last EPOS document, including pharmacists, nurses, specialised care givers and indeed patients themselves, who employ increasing self-management of their condition using over the counter treatments. The document provides suggestions for future research in this area and offers updated guidance for definitions and outcome measurements in research in different settings. EPOS2020 contains chapters on definitions and classification where we have defined a large number of terms and indicated preferred terms. A new classification of CRS into primary and secondary CRS and further division into localized and diffuse disease, based on anatomic distribution is proposed. There are extensive chapters on epidemiology and predisposing factors, inflammatory mechanisms, (differential) diagnosis of facial pain, allergic rhinitis, genetics, cystic fibrosis, aspirin exacerbated respiratory disease, immunodeficiencies, allergic fungal rhinosinusitis and the relationship between upper and lower airways. The chapters on paediatric acute and chronic rhinosinusitis are totally rewritten. All available evidence for the management of acute rhinosinusitis and chronic rhinosinusitis with or without nasal polyps in adults and children is systematically reviewed and integrated care pathways based on the evidence are proposed. Despite considerable increases in the amount of quality publications in recent years, a large number of practical clinical questions remain. It was agreed that the best way to address these was to conduct a Delphi exercise . The results have been integrated into the respective sections. Last but not least, advice for patients and pharmacists and a new list of research needs are included. The full document can be downloaded for free on the website of this journal: http://www.rhinologyjournal.com.

/pdf/european-position-paper-on-rhinosinusitis-and-nasal-polyps-mj734vsl7p.pdf

European Position Paper on Rhinosinusitis and Nasal Polyps 2020

Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target-domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. Due to the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning research studies, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Unlike previous surveys, this survey article reviews more than 40 representative transfer learning approaches, especially homogeneous transfer learning approaches, from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, over 20 representative transfer learning models are used for experiments. The models are performed on three different data sets, that is, Amazon Reviews, Reuters-21578, and Office-31, and the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.

A Comprehensive Survey on Transfer Learning

Independent Component Analysis.

Imitation learning is a data-driven approach that has proven to be successful in building autonomous navigation systems. One of the key tasks in imitation learning is collecting data, but data only collected by humans cannot include many types of data, such as deviating from the target path. If we use a model trained with such data, the deviation will accumulate, and returning to the target path will be difficult. Related studies have demonstrated the importance of correction data, and two types of solutions have been proposed: data augmentation and online sampling. In this paper, we propose a new online sampling method for acquiring correction data that is safe and effective, which uses a device that detects the force applied a steering wheel and accelerator pedal during an intervention. Autonomous navigation experiments are conducted using small vehicles to follow a specified path in static and dynamic environments. Our experimental results show that we can successfully separate intervention data from all collected data using intervention force and that using intervention data for model training is effective for improving the route-following. Also, our model can perform obstacle avoidance and generate appropriate control signals when encountering dynamic objects, such as pedestrians, at specific locations.

Intervention Force-based Imitation Learning for Autonomous Navigation in Dynamic Environments

Audio-Visual Speech Recognition (AVSR) is one of techniques to enhance robustness of speech recognizer in noisy or real environments. On the other hand, Deep Neural Networks (DNNs) have recently attracted a lot of attentions of researchers in the speech recognition field, because we can drastically improve recognition performance by using DNNs. There are two ways to employ DNN techniques for speech recognition: a hybrid approach and a tandem approach; in the hybrid approach an emission probability on each Hidden Markov Model (HMM) state is computed using a DNN, while in the tandem approach a DNN is composed into a feature extraction scheme. In this paper, we investigate and compare several DNN-based AVSR methods to mainly clarify how we should incorporate audio and visual modalities using DNNs. We carried out recognition experiments using a corpus CENSREC-1-AV, and we discuss the results to find out the best DNN-based AVSR modeling. Then it turns out that a tandem-based method using audio Deep Bottle-Neck Features (DBNFs) and visual ones with multi-stream HMMs is the most suitable, followed by a hybrid approach and another tandem scheme using audio-visual DBNFs.

/pdf/investigation-of-dnn-based-audio-visual-speech-recognition-2r6jia5i2n.pdf

Investigation of DNN-Based Audio-Visual Speech Recognition (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)

We study the effect of cognitive states, feelings about tasks, on grasping behavior to estimate user's feelings from their motion. Since people solve the inverse kinematics problem of grasping based on their cognition for the task, when they grasp an object, the way to grasp the object reflects their cognitive states. We are analyzing the way of grasping a cup depending on whether a user is stressed. The physical properties of grasping, volume and entropy of Grasp Jacobian ellipsoids are analyzed. The volume of Grasp Jacobian ellipsoids, which indicates the possible size of object movement, was shrunk after learning the grasp motion. Also the volumes between the relaxed and the stressed cognitive conditions were significantly different. These results show that the user's cognition for tasks reflects the grasp forms and the possible size of object movement.

Analyzing grasping for inferring cognitive states of users

Transformer-based models have gained popularity in the field of natural language processing (NLP) and are extensively utilized in computer vision tasks and multi-modal models such as GPT4. This paper presents a novel method to enhance the explainability of Transformer-based image classification models. Our method aims to improve trust in classification results and empower users to gain a deeper understanding of the model for downstream tasks by providing visualizations of class-specific maps. We introduce two modules: the ``Relationship Weighted Out"and the ``Cut"modules. The ``Relationship Weighted Out"module focuses on extracting class-specific information from intermediate layers, enabling us to highlight relevant features. Additionally, the ``Cut"module performs fine-grained feature decomposition, taking into account factors such as position, texture, and color. By integrating these modules, we generate dense class-specific visual explainability maps. We validate our method with extensive qualitative and quantitative experiments on the ImageNet dataset. Furthermore, we conduct a large number of experiments on the LRN dataset, specifically designed for automatic driving danger alerts, to evaluate the explainability of our method in complex backgrounds. The results demonstrate a significant improvement over previous methods. Moreover, we conduct ablation experiments to validate the effectiveness of each module. Through these experiments, we are able to confirm the respective contributions of each module, thus solidifying the overall effectiveness of our proposed approach.

R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut

In this paper we propose an interactive system that allows only the owner of a target object to secretly find it among other similar or identical objects, which we call SecretSign. Finding a personal object, e.g., an assigned vehicle in a car-sharing parking lot, where there are many cars that look the same or are similar, can be difficult. In addition, we may not want to notify other people which object we are looking for, e.g., a car thief waiting to steal a car when the driver opens the door. Our proposed system allows a user to find an object without notifying others of the target, using a light attached to the target object which turns on and off in conjunction with user's operation of a remote control device, while lights on the other objects turn on and off randomly. We experimentally evaluated the system, in both virtual and real-world environments, and verified that SecretSign enabled users to quickly find their target objects without revealing the target to observers.

Kazuya Takeda

Papers

Intervention Force-based Imitation Learning for Autonomous Navigation in Dynamic Environments

Investigation of DNN-Based Audio-Visual Speech Recognition (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)

Analyzing grasping for inferring cognitive states of users

R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut

SecretSign: A Method of Finding an Off-Line Target Object without Revealing the Target to Observers