The document summarizes a paper that conducted a reproducible and fair comparison of recent domain generalization (DG) methods. The key points are:
1. Many DG methods have been proposed recently but lack common experimental settings, making results difficult to compare.
2. The study implemented 14 DG methods on 7 datasets using a common framework to enable fair comparisons.
3. Surprisingly, simple empirical risk minimization performed competitively with state-of-the-art DG methods under the controlled settings.
4. The authors made their code openly available to help advance DG research.
The document discusses leveraged Gaussian processes and their applications to learning from demonstration and uncertainty modeling. It introduces key concepts such as Gaussian processes, leveraged Gaussian processes, leveraged optimization, and uncertainty modeling in deep learning. It also discusses several applications including using both positive and negative demonstrations, learning from demonstration, and incorporating data with mixed qualities without explicit labeling.
Introduction to Graph neural networks @ Vienna Deep Learning meetupLiad Magen
Graphs are useful data structures that can be used to model various sorts of data: from molecular protein structures to social networks, pandemic spreading models, and visually rich content such as websites & invoices. In the recent few years, graph neural networks have done a huge leap forward. It is a powerful tool that every data scientist should know. In this talk, we will review their basic structure, show some example usages, and explore the existing (python) tools.
The document summarizes a paper that conducted a reproducible and fair comparison of recent domain generalization (DG) methods. The key points are:
1. Many DG methods have been proposed recently but lack common experimental settings, making results difficult to compare.
2. The study implemented 14 DG methods on 7 datasets using a common framework to enable fair comparisons.
3. Surprisingly, simple empirical risk minimization performed competitively with state-of-the-art DG methods under the controlled settings.
4. The authors made their code openly available to help advance DG research.
The document discusses leveraged Gaussian processes and their applications to learning from demonstration and uncertainty modeling. It introduces key concepts such as Gaussian processes, leveraged Gaussian processes, leveraged optimization, and uncertainty modeling in deep learning. It also discusses several applications including using both positive and negative demonstrations, learning from demonstration, and incorporating data with mixed qualities without explicit labeling.
Introduction to Graph neural networks @ Vienna Deep Learning meetupLiad Magen
Graphs are useful data structures that can be used to model various sorts of data: from molecular protein structures to social networks, pandemic spreading models, and visually rich content such as websites & invoices. In the recent few years, graph neural networks have done a huge leap forward. It is a powerful tool that every data scientist should know. In this talk, we will review their basic structure, show some example usages, and explore the existing (python) tools.
PEGASUS is a large Transformer-based model for abstractive text summarization. It uses a novel pre-training objective called gap-sentence generation (GSG) which masks sentences from input documents and trains the model to generate the missing sentences. GSG more closely resembles the downstream summarization task compared to other objectives. In experiments, PEGASUS achieved state-of-the-art results on 12 summarization datasets using GSG pre-training and outperformed other models when fine-tuned on limited data.
This document discusses various methods for calculating Wasserstein distance between probability distributions, including:
- Sliced Wasserstein distance, which projects distributions onto lower-dimensional spaces to enable efficient 1D optimal transport calculations.
- Max-sliced Wasserstein distance, which focuses sampling on the most informative projection directions.
- Generalized sliced Wasserstein distance, which uses more flexible projection functions than simple slicing, like the Radon transform.
- Augmented sliced Wasserstein distance, which applies a learned transformation to distributions before projecting, allowing more expressive matching between distributions.
These sliced/generalized Wasserstein distances have been used as loss functions for generative models with promising
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...ddnpaa
(参考文献)Shengnan Guo, Youfang Lin, Ning Feng, Chao Song, and Huaiyu Wan. Attention based spatial-temporal graph convolutional networks
for traffic flow forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 922–929, 2019.
Interpretability beyond feature attribution quantitative testing with concept...MLconf
TCAV is a method for interpreting machine learning models by quantitatively measuring the importance of user-chosen concepts for a model's predictions, even if those concepts were not part of the model's training data or input features. It does this by learning concept activation vectors (CAVs) that represent concepts and using the CAVs to calculate a model's sensitivity or importance to each concept via directional derivatives. TCAV was shown to validate ground truths from sanity check experiments, uncover geographical biases in widely used models, and match domain expert concepts for diabetic retinopathy versus those a model may use, helping ensure models' values and knowledge are properly aligned and reflected.
The document discusses image style transfer and machine learning applications for iOS. It introduces neural style transfer using convolutional neural networks. It describes using feature maps from VGG networks to calculate content and style losses for transferring style between images. It also discusses using CoreML and Apple's Vision framework to easily integrate pre-trained models into iOS apps for tasks like face detection, object recognition and style transfer.
1. Two papers on unsupervised domain adaptation were presented at ICML2018: "Learning Semantic Representations for Unsupervised Domain Adaptation" and "CyCADA: Cycle-Consistent Adversarial Domain Adaptation".
2. The CyCADA paper uses cycle-consistent adversarial domain adaptation with cycle GAN to translate images at the pixel level while also aligning representations at the semantic level.
3. The semantic representation paper uses semantic alignment and introduces techniques like adding noise to improve over previous semantic alignment methods.
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsJinwon Lee
The document presents SimCLR, a framework for contrastive learning of visual representations using simple data augmentation. Key aspects of SimCLR include using random cropping and color distortions to generate positive sample pairs for the contrastive loss, a nonlinear projection head to learn representations, and large batch sizes. Evaluation shows SimCLR learns representations that outperform supervised pretraining on downstream tasks and achieves state-of-the-art results with only view augmentation and contrastive loss.
Neural Network Based Individual Classification SystemIRJET Journal
This document describes a neural network model developed for individual classification. The model was designed to measure personality traits through a questionnaire. It then uses a neural network trained on sample data through unsupervised and supervised learning with multi-layer perceptions. The backpropagation algorithm was used to train the network. The neural network architecture included multiple neuron layers trained on a 200 item data set, achieving 99.82% accuracy. The goal was to classify individuals into high, middle, and low personality categories for use in job selection or training.
PEGASUS is a large Transformer-based model for abstractive text summarization. It uses a novel pre-training objective called gap-sentence generation (GSG) which masks sentences from input documents and trains the model to generate the missing sentences. GSG more closely resembles the downstream summarization task compared to other objectives. In experiments, PEGASUS achieved state-of-the-art results on 12 summarization datasets using GSG pre-training and outperformed other models when fine-tuned on limited data.
This document discusses various methods for calculating Wasserstein distance between probability distributions, including:
- Sliced Wasserstein distance, which projects distributions onto lower-dimensional spaces to enable efficient 1D optimal transport calculations.
- Max-sliced Wasserstein distance, which focuses sampling on the most informative projection directions.
- Generalized sliced Wasserstein distance, which uses more flexible projection functions than simple slicing, like the Radon transform.
- Augmented sliced Wasserstein distance, which applies a learned transformation to distributions before projecting, allowing more expressive matching between distributions.
These sliced/generalized Wasserstein distances have been used as loss functions for generative models with promising
【論文紹介】 Attention Based Spatial-Temporal Graph Convolutional Networks for Traf...ddnpaa
(参考文献)Shengnan Guo, Youfang Lin, Ning Feng, Chao Song, and Huaiyu Wan. Attention based spatial-temporal graph convolutional networks
for traffic flow forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 922–929, 2019.
Interpretability beyond feature attribution quantitative testing with concept...MLconf
TCAV is a method for interpreting machine learning models by quantitatively measuring the importance of user-chosen concepts for a model's predictions, even if those concepts were not part of the model's training data or input features. It does this by learning concept activation vectors (CAVs) that represent concepts and using the CAVs to calculate a model's sensitivity or importance to each concept via directional derivatives. TCAV was shown to validate ground truths from sanity check experiments, uncover geographical biases in widely used models, and match domain expert concepts for diabetic retinopathy versus those a model may use, helping ensure models' values and knowledge are properly aligned and reflected.
The document discusses image style transfer and machine learning applications for iOS. It introduces neural style transfer using convolutional neural networks. It describes using feature maps from VGG networks to calculate content and style losses for transferring style between images. It also discusses using CoreML and Apple's Vision framework to easily integrate pre-trained models into iOS apps for tasks like face detection, object recognition and style transfer.
1. Two papers on unsupervised domain adaptation were presented at ICML2018: "Learning Semantic Representations for Unsupervised Domain Adaptation" and "CyCADA: Cycle-Consistent Adversarial Domain Adaptation".
2. The CyCADA paper uses cycle-consistent adversarial domain adaptation with cycle GAN to translate images at the pixel level while also aligning representations at the semantic level.
3. The semantic representation paper uses semantic alignment and introduces techniques like adding noise to improve over previous semantic alignment methods.
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsJinwon Lee
The document presents SimCLR, a framework for contrastive learning of visual representations using simple data augmentation. Key aspects of SimCLR include using random cropping and color distortions to generate positive sample pairs for the contrastive loss, a nonlinear projection head to learn representations, and large batch sizes. Evaluation shows SimCLR learns representations that outperform supervised pretraining on downstream tasks and achieves state-of-the-art results with only view augmentation and contrastive loss.
Neural Network Based Individual Classification SystemIRJET Journal
This document describes a neural network model developed for individual classification. The model was designed to measure personality traits through a questionnaire. It then uses a neural network trained on sample data through unsupervised and supervised learning with multi-layer perceptions. The backpropagation algorithm was used to train the network. The neural network architecture included multiple neuron layers trained on a 200 item data set, achieving 99.82% accuracy. The goal was to classify individuals into high, middle, and low personality categories for use in job selection or training.
Regularization techniques like dropout and max-norm regularization help reduce overfitting in deep learning models. Dropout prevents overfitting by randomly ignoring nodes during training, ensuring nodes are not codependent. Max-norm regularization constrains weight vectors to have an L2 norm below a set value r to prevent large weights that overly fit the training data. Both techniques improve model generalization to unseen data compared to non-regularized networks, though dropout training may take longer.
Evolutionary Algorithm for Optimal Connection Weights in Artificial Neural Ne...CSCJournals
A neural network may be considered as an adaptive system that progressively self-organizes in order to approximate the solution, making the problem solver free from the need to accurately and unambiguously specify the steps towards the solution. Moreover, Evolutionary Artificial Neural Networks (EANNs) have the ability to progressively improve their performance on a given task by executing learning. An evolutionary computation gives adaptability for connection weights using feed forward architecture. In this paper, the use of evolutionary computation for feed-forward neural network learning is discussed. To check the validation of proposed method, XOR benchmark problem has been used. The accuracy of the proposed model is more satisfactory as compared to gradient method.
1. Decorrelated Batch Normalization (DBN) whitens activations within each layer using ZCA whitening to avoid stochastic axis swapping caused by PCA whitening.
2. DBN improves conditioning and speeds up convergence compared to Batch Normalization by achieving approximate dynamical isometry and diagonalizing the Fisher Information Matrix.
3. Experiments on multilayer perceptrons and convolutional neural networks show that DBN outperforms Batch Normalization, and can be used to train deeper and wider residual networks.
Comparison of Neural Network Training Functions for Hematoma Classification i...IOSR Journals
Classification is one of the most important task in application areas of artificial neural networks
(ANN).Training neural networks is a complex task in the supervised learning field of research. The main
difficulty in adopting ANN is to find the most appropriate combination of learning, transfer and training
function for the classification task. We compared the performances of three types of training algorithms in feed
forward neural network for brain hematoma classification. In this work we have selected Gradient Descent
based backpropagation, Gradient Descent with momentum, Resilence backpropogation algorithms. Under
conjugate based algorithms, Scaled Conjugate back propagation, Conjugate Gradient backpropagation with
Polak-Riebreupdates(CGP) and Conjugate Gradient backpropagation with Fletcher-Reeves updates (CGF).The
last category is Quasi Newton based algorithm, under this BFGS, Levenberg-Marquardt algorithms are
selected. Proposed work compared training algorithm on the basis of mean square error, accuracy, rate of
convergence and correctness of the classification. Our conclusion about the training functions is based on the
simulation results
Neural networks for the prediction and forecasting of water resources variablesJonathan D'Cruz
This document reviews the use of artificial neural networks (ANNs) for predicting and forecasting water resource variables. It outlines the key steps in developing ANN models, including choosing performance criteria, preprocessing and dividing data, determining appropriate model inputs and network architecture, optimizing connection weights through training, and validating models. Specifically, it focuses on feedforward networks with sigmoid transfer functions, which have been most widely used for predicting water resources variables.
Hybrid Quantum Genetic Particle Swarm Optimization Algorithm For Solving Opti...paperpublications3
Abstract: This paper presents hybrid particle swarm algorithm for solving the multi-objective reactive power dispatch problem. Modal analysis of the system is used for static voltage stability assessment. Loss minimization and maximization of voltage stability margin are taken as the objectives. Generator terminal voltages, reactive power generation of the capacitor banks and tap changing transformer setting are taken as the optimization variables. Evolutionary algorithm and Swarm Intelligence algorithm (EA, SI), a part of Bio inspired optimization algorithm, have been widely used to solve numerous optimization problem in various science and engineering domains. In this paper, a framework of hybrid particle swarm optimization algorithm, called Hybrid quantum genetic particle swarm optimization (HQGPSO), is proposed by reasonably combining the Q-bit evolutionary search of quantum particle swarm optimization (QPSO) algorithm and binary bit evolutionary search of genetic particle swarm optimization (GPSO) in order to achieve better optimization performances. The proposed HQGPSO also can be viewed as a kind of hybridization of micro-space based search and macro-space based search, which enriches the searching behavior to enhance and balance the exploration and exploitation abilities in the whole searching space. In order to evaluate the proposed algorithm, it has been tested on IEEE 30 bus system and compared to other algorithms.
Keywords: quantum particle swarm optimization, genetic particle swarm optimization, hybrid algorithm Optimization, Swarm Intelligence, optimal reactive power, Transmission loss.
This document provides an overview of machine learning concepts related to supervised learning. It discusses perceptron models, which are simple linear classifiers that can be trained with algorithms like gradient descent. Gradient descent and stochastic gradient descent are described as methods for updating perceptron weights to minimize error. The document also introduces common supervised learning algorithms for classification tasks like naive Bayes, decision trees, logistic regression, and support vector machines. Popular machine learning applications that use classification are also mentioned.
Handling Imbalanced Data: SMOTE vs. Random UndersamplingIRJET Journal
This document compares different techniques for handling imbalanced data, including random undersampling and SMOTE (Synthetic Minority Over-sampling Technique), using two machine learning classifiers - Random Forest and XGBoost. It finds that XGBoost generally performs better than Random Forest across different sampling techniques in terms of metrics like AUC, sensitivity and specificity. Random undersampling with XGBoost provided the most balanced results on the randomly generated imbalanced dataset used in this study. SMOTE without proper validation gave the best numerical results but likely overfit the data.
A COMPARATIVE STUDY OF BACKPROPAGATION ALGORITHMS IN FINANCIAL PREDICTIONIJCSEA Journal
Stock market price index prediction is a challenging task for investors and scholars. Artificial neural networks have been widely employed to predict financial stock market levels thanks to their ability to model nonlinear functions. The accuracy of backpropagation neural networks trained with different heuristic and numerical algorithms is measured for comparison purpose. It is found that numerical algorithm outperform heuristic techniques.
PR-330: How To Train Your ViT? Data, Augmentation, and Regularization in Visi...Jinwon Lee
The document summarizes a study on training Vision Transformers (ViTs) by exploring different combinations of data augmentation, regularization techniques, model sizes, and training dataset sizes. Some key findings include: 1) Models trained with extensive data augmentation on ImageNet-1k performed comparably to those trained on the larger ImageNet-21k dataset without augmentation. 2) Transfer learning from pre-trained models was more efficient and achieved better results than training models from scratch, even with extensive compute. 3) Models pre-trained on more data showed better transfer ability, indicating more data yields more generic representations.
Learning Sparse Networks using Targeted DropoutSeunghyun Hwang
Targeted dropout is a technique that applies dropout primarily to network units and weights that are believed to be less useful based on their magnitudes. This makes networks robust to post-hoc pruning while achieving high sparsity. Experiments on ResNet, Wide ResNet and Transformer models on image and text tasks achieved up to 99% sparsity with less than 4% accuracy drop. Scheduling the targeting proportion and dropout rates over time was found to improve results compared to random pruning before training. Targeted dropout is an effective regularization method for training networks that can be heavily pruned after training.
A hybrid constructive algorithm incorporating teaching-learning based optimiz...IJECEIAES
The document describes a hybrid algorithm that combines a modified multiple operations using statistical tests (MMOST) constructive algorithm with an improved teaching-learning based optimization (ITLBO) algorithm for neural network training. The hybrid algorithm simultaneously optimizes the neural network structure and weights. The MMOST algorithm constructs different network structures, while the ITLBO algorithm finds the optimal weights for each structure. The hybrid algorithm, called MCO-ITLBO, is tested on classification and time series prediction problems and is shown to outperform other algorithms in terms of error rates and network complexity. Experimental results demonstrate that the MCO-ITLBO algorithm provides better performance than algorithms using only constructive or training methods.
This document compares the performance of two neural network architectures, multi-layer perceptron (MLP) and radial basis function (RBF) networks, on a face recognition system. It trains MLP networks using different variants of the backpropagation algorithm and compares the results to RBF networks. The document finds that RBF networks provide better generalization performance compared to backpropagation algorithms and have faster training times, making them more suitable for face recognition.
Enhancing energy efficient dynamic load balanced clustering protocol using Dy...IJTET Journal
Mobile Ad hoc Network (MANET) is a kind of self configuring and self describing wireless ad hoc networks. MANET has characteristics of topology dynamics due to factors such as energy conservation and node movement that leads to dynamic load balanced clustering problem (DLBCP). It is necessary to have an effective clustering algorithm for adapting the topology change. Generally, Clustering is mainly used to reduce the topology size. In this, we used load balance and energy metric in GA to solve the DLBCP. It is important to select the energy efficient cluster head for maintaining the cluster structure and balance the load effectively. Elitism based Immigrants Genetic algorithm (EIGA) and Memory Enhanced Genetic Algorithm (MEGA) are used to solve DLBCP. These schemes will select the optimal cluster head by considering the parameters includes distance and energy. We used EIGA to maintain the diversity level of the population and memory scheme (MEGA) to store the old environments into the memory. It promises the energy efficiency for the entire cluster structure to increase the lifetime of the network. The experimental results show that the proposed schemes increases the network life time and reduces the energy consumption.
IRJET- Analysis of Vehicle Number Plate RecognitionIRJET Journal
This document summarizes research on techniques for enhancing license plate images and improving vehicle number plate recognition. It discusses using forward motion deblurring, scale-based region growing, blur estimation, blind image deblurring, and a no-reference metric to enhance license plate image details and obtain deblurred images. The document also reviews related work applying these and other techniques, such as binary SIFT, energy cooperation in wireless networks, and parametric blur estimation for natural image restoration. The goal is to develop more accurate and robust methods for automatic license plate recognition.
This document provides information on several 2015 IEEE Matlab projects related to signal processing and image analysis. It lists the project titles, languages, links, and abstracts for 10 different Matlab projects. The projects cover topics such as target source separation using deep neural networks, hyperspectral image classification using sparse representation, image denoising techniques, and cardiovascular biometrics.
Dr. Fariba Fahroo presents an overview of her program, Optimization and Discrete Mathematics, at the AFOSR 2013 Spring Review. At this review, Program Officers from AFOSR Technical Divisions will present briefings that highlight basic research programs beneficial to the Air Force.
Similar to [PR12] Spectral Normalization for Generative Adversarial Networks (20)
[CVPR2020] Simple but effective image enhancement techniquesJaeJun Yoo
The document discusses several image enhancement techniques:
1. WCT2, which uses wavelet transforms for photorealistic style transfer, achieving faster and lighter models than previous techniques.
2. CutBlur, a new data augmentation method that improves performance on super-resolution and other low-level vision tasks by adding blur and cutting patches from images.
3. SimUSR, a simple but strong baseline for unsupervised super-resolution that achieves state-of-the-art results using only a single low-resolution image during training.
Super resolution in deep learning era - Jaejun YooJaeJun Yoo
1) The document discusses super-resolution techniques in deep learning, including inverse problems, image restoration problems, and different deep learning models.
2) Early models like SRCNN used convolutional networks for super-resolution but were shallow, while later models incorporated residual learning (VDSR), recursive learning (DRCN), and became very deep and dense (SRResNet).
3) Key developments included EDSR which provided a strong backbone model and GAN-based approaches like SRGAN which aimed to generate more realistic textures but require new evaluation metrics.
A beginner's guide to Style Transfer and recent trendsJaeJun Yoo
Style transfer techniques have evolved from matching gram matrices to using neural networks. Early methods matched gram statistics of CNN features to transfer texture styles. Recent work uses adaptive instance normalization and feed-forward networks. WCT2 achieves photorealistic transfer using wavelet transforms that satisfy the perfect reconstruction condition, enabling high resolution stylization and temporal consistency in videos without post-processing.
This paper proposes AmbientGAN, which trains a generative adversarial network using partial or noisy observations rather than fully observed samples. AmbientGAN trains the discriminator on the measurement domain rather than the raw data domain, allowing the generator to be trained without needing large amounts of good training data. The paper proves it is theoretically possible to recover the original data distribution even when the measurement process is not invertible. It presents experimental results showing AmbientGAN can generate high quality samples and recover the underlying data distribution from various types of lossy and noisy measurements.
[PR12] categorical reparameterization with gumbel softmaxJaeJun Yoo
(Korean) Introduction to (paper1) Categorical Reparameterization with Gumbel Softmax and (paper2) The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
Video: https://youtu.be/ty3SciyoIyk
Paper1: https://arxiv.org/abs/1611.01144
Paper2: https://arxiv.org/abs/1611.00712
[PR12] understanding deep learning requires rethinking generalizationJaeJun Yoo
The document discusses a paper that argues traditional theories of generalization may not fully explain why large neural networks generalize well in practice. It summarizes the paper's key points:
1) The paper shows neural networks can easily fit random labels, calling into question traditional measures of complexity.
2) Regularization helps but is not the fundamental reason for generalization. Neural networks have sufficient capacity to memorize data.
3) Implicit biases in algorithms like SGD may better explain generalization by driving solutions toward minimum norm.
4) The paper suggests rethinking generalization as the effective capacity of neural networks may differ from theoretical measures. Understanding finite sample expressivity is important.
The document discusses capsule networks, a type of neural network proposed by Geoff Hinton in 2017 as an alternative to convolutional neural networks (CNNs) for computer vision tasks. Capsule networks aim to address some limitations of CNNs, such as their inability to capture spatial relationships and pose information. The key concepts discussed include dynamic routing between capsules, which allows for parts-based representation, and equivariance, where capsules can learn transformation properties like position and orientation. The document provides an overview of a capsule network architecture and routing algorithm proposed in a 2017 paper by Sabour et al.
[PR12] Inception and Xception - Jaejun YooJaeJun Yoo
This document discusses Inception and Xception models for computer vision tasks. It describes the Inception architecture, which uses 1x1, 3x3 and 5x5 convolutional filters arranged in parallel to capture correlations at different scales more efficiently. It also describes the Xception model, which entirely separates cross-channel correlations and spatial correlations using depthwise separable convolutions. The document compares different approaches for reducing computational costs like pooling and strided convolutions.
Introduction to domain adversarial training of neural network.
(Kor) video : https://www.youtube.com/watch?v=n2J7giHrS-Y&t=1s
Papers: A survey on transfer learning, SJ Pan 2009 / A theory of learning from different domains, S Ben-David et al. 2010 / Domain-Adversarial Training of Neural Networks, Y Ganin 2016
Slides I refered:
http://www.di.ens.fr/~germain/talks/nips2014_dann_slides.pdf
http://john.blitzer.com/talks/icmltutorial_2010.pdf (DA theory part)
https://epat2014.sciencesconf.org/conference/epat2014/pages/slides_DA_epat_17.pdf (DA theory part)
https://www.slideshare.net/butest/ppt-3860159 (DA theory part)
Picked-up lists of GAN variants which provided insights to the community. (GANs-Improved GANs-DCGAN-Unrolled GAN-InfoGAN-f-GAN-EBGAN-WGAN)
After short introduction to GANs, we look through the remaining difficulties of standard GANs and their temporary solutions (Improved GANs). By following the slides, we can see the other solutions which tried to resolve the problems in various ways, e.g. careful architecture selection (DCGAN), slight change in update (Unrolled GAN), additional constraint (InfoGAN), generalization of the loss function using various divergence (f-GAN), providing new framework of energy based model (EBGAN), another step of generalization of the loss function (WGAN).
Immersive Learning That Works: Research Grounding and Paths ForwardLeonel Morgado
We will metaverse into the essence of immersive learning, into its three dimensions and conceptual models. This approach encompasses elements from teaching methodologies to social involvement, through organizational concerns and technologies. Challenging the perception of learning as knowledge transfer, we introduce a 'Uses, Practices & Strategies' model operationalized by the 'Immersive Learning Brain' and ‘Immersion Cube’ frameworks. This approach offers a comprehensive guide through the intricacies of immersive educational experiences and spotlighting research frontiers, along the immersion dimensions of system, narrative, and agency. Our discourse extends to stakeholders beyond the academic sphere, addressing the interests of technologists, instructional designers, and policymakers. We span various contexts, from formal education to organizational transformation to the new horizon of an AI-pervasive society. This keynote aims to unite the iLRN community in a collaborative journey towards a future where immersive learning research and practice coalesce, paving the way for innovative educational research and practice landscapes.
Mending Clothing to Support Sustainable Fashion_CIMaR 2024.pdfSelcen Ozturkcan
Ozturkcan, S., Berndt, A., & Angelakis, A. (2024). Mending clothing to support sustainable fashion. Presented at the 31st Annual Conference by the Consortium for International Marketing Research (CIMaR), 10-13 Jun 2024, University of Gävle, Sweden.
PPT on Direct Seeded Rice presented at the three-day 'Training and Validation Workshop on Modules of Climate Smart Agriculture (CSA) Technologies in South Asia' workshop on April 22, 2024.
Describing and Interpreting an Immersive Learning Case with the Immersion Cub...Leonel Morgado
Current descriptions of immersive learning cases are often difficult or impossible to compare. This is due to a myriad of different options on what details to include, which aspects are relevant, and on the descriptive approaches employed. Also, these aspects often combine very specific details with more general guidelines or indicate intents and rationales without clarifying their implementation. In this paper we provide a method to describe immersive learning cases that is structured to enable comparisons, yet flexible enough to allow researchers and practitioners to decide which aspects to include. This method leverages a taxonomy that classifies educational aspects at three levels (uses, practices, and strategies) and then utilizes two frameworks, the Immersive Learning Brain and the Immersion Cube, to enable a structured description and interpretation of immersive learning cases. The method is then demonstrated on a published immersive learning case on training for wind turbine maintenance using virtual reality. Applying the method results in a structured artifact, the Immersive Learning Case Sheet, that tags the case with its proximal uses, practices, and strategies, and refines the free text case description to ensure that matching details are included. This contribution is thus a case description method in support of future comparative research of immersive learning cases. We then discuss how the resulting description and interpretation can be leveraged to change immersion learning cases, by enriching them (considering low-effort changes or additions) or innovating (exploring more challenging avenues of transformation). The method holds significant promise to support better-grounded research in immersive learning.
Current Ms word generated power point presentation covers major details about the micronuclei test. It's significance and assays to conduct it. It is used to detect the micronuclei formation inside the cells of nearly every multicellular organism. It's formation takes place during chromosomal sepration at metaphase.
The cost of acquiring information by natural selectionCarl Bergstrom
This is a short talk that I gave at the Banff International Research Station workshop on Modeling and Theory in Population Biology. The idea is to try to understand how the burden of natural selection relates to the amount of information that selection puts into the genome.
It's based on the first part of this research paper:
The cost of information acquisition by natural selection
Ryan Seamus McGee, Olivia Kosterlitz, Artem Kaznatcheev, Benjamin Kerr, Carl T. Bergstrom
bioRxiv 2022.07.02.498577; doi: https://doi.org/10.1101/2022.07.02.498577
Authoring a personal GPT for your research and practice: How we created the Q...Leonel Morgado
Thematic analysis in qualitative research is a time-consuming and systematic task, typically done using teams. Team members must ground their activities on common understandings of the major concepts underlying the thematic analysis, and define criteria for its development. However, conceptual misunderstandings, equivocations, and lack of adherence to criteria are challenges to the quality and speed of this process. Given the distributed and uncertain nature of this process, we wondered if the tasks in thematic analysis could be supported by readily available artificial intelligence chatbots. Our early efforts point to potential benefits: not just saving time in the coding process but better adherence to criteria and grounding, by increasing triangulation between humans and artificial intelligence. This tutorial will provide a description and demonstration of the process we followed, as two academic researchers, to develop a custom ChatGPT to assist with qualitative coding in the thematic data analysis process of immersive learning accounts in a survey of the academic literature: QUAL-E Immersive Learning Thematic Analysis Helper. In the hands-on time, participants will try out QUAL-E and develop their ideas for their own qualitative coding ChatGPT. Participants that have the paid ChatGPT Plus subscription can create a draft of their assistants. The organizers will provide course materials and slide deck that participants will be able to utilize to continue development of their custom GPT. The paid subscription to ChatGPT Plus is not required to participate in this workshop, just for trying out personal GPTs during it.
(June 12, 2024) Webinar: Development of PET theranostics targeting the molecu...Scintica Instrumentation
Targeting Hsp90 and its pathogen Orthologs with Tethered Inhibitors as a Diagnostic and Therapeutic Strategy for cancer and infectious diseases with Dr. Timothy Haystead.
The debris of the ‘last major merger’ is dynamically youngSérgio Sacani
The Milky Way’s (MW) inner stellar halo contains an [Fe/H]-rich component with highly eccentric orbits, often referred to as the
‘last major merger.’ Hypotheses for the origin of this component include Gaia-Sausage/Enceladus (GSE), where the progenitor
collided with the MW proto-disc 8–11 Gyr ago, and the Virgo Radial Merger (VRM), where the progenitor collided with the
MW disc within the last 3 Gyr. These two scenarios make different predictions about observable structure in local phase space,
because the morphology of debris depends on how long it has had to phase mix. The recently identified phase-space folds in Gaia
DR3 have positive caustic velocities, making them fundamentally different than the phase-mixed chevrons found in simulations
at late times. Roughly 20 per cent of the stars in the prograde local stellar halo are associated with the observed caustics. Based
on a simple phase-mixing model, the observed number of caustics are consistent with a merger that occurred 1–2 Gyr ago.
We also compare the observed phase-space distribution to FIRE-2 Latte simulations of GSE-like mergers, using a quantitative
measurement of phase mixing (2D causticality). The observed local phase-space distribution best matches the simulated data
1–2 Gyr after collision, and certainly not later than 3 Gyr. This is further evidence that the progenitor of the ‘last major merger’
did not collide with the MW proto-disc at early times, as is thought for the GSE, but instead collided with the MW disc within
the last few Gyr, consistent with the body of work surrounding the VRM.
2. Today’s contents
Spectral Normalization for Generative Adversarial Networks
by Takeru Miyato, Toshiki Kataoka, Masanori Koyama, Yuichi Yoshida
Feb. 2018: https://arxiv.org/abs/1802.05957
Accept: (Oral)
Rating: 8-8-8
ICLR 2018
3. Motivation & Contribution
“One of the challenges in the study of generative
adversarial networks is the instability of its training.”
: Proposed a novel weight normalization technique called
spectral normalization to stabilize the training of the
discriminator of GANs.
• Lipschitz constant is the only hyper-parameter to be tuned,
and the algorithm does not require intensive tuning of the
only hyper-parameter for satisfactory performance.
• Implementation is simple and the additional computational
cost is small.
8. GANs is hard to train… why?
WGAN, GAN-GP
While input based regularizations allow for relatively easy formulations
based on samples, they also suffer from the fact that, they cannot
impose regularization on the space outside of the supports of the
generator and data distributions without introducing somewhat
heuristic means.
15. Why SN is better than…
… Gradient Penalty
• The approach has an obvious weakness of being heavily dependent on the support of
the current generative distribution. As a matter of course, the generative distribution
and its support gradually changes in the course of the training, and this can
destabilize the effect of such regularization.
• While this seems to serve the same purpose as spectral normalization, orthonormal
regularization are mathematically quite different from our spectral normalization
because the orthonormal regularization destroys the information about the spectrum
by setting all the singular values to one. On the other hand, spectral normalization
only scales the spectrum so that the its maximum will be one.
… Orthonormal Regularization
22. Summary
They proposed a novel weight normalization technique
called spectral normalization to stabilize the training of the
discriminator of GANs
• in various network architectures
• in various hyperparameter settings
• in various datasets
• with an intuitive and straight forward idea
• only using a relatively easy linear algebra knowledge
Practicality
Principled way