Phases of learning dynamics in artificial neural networks in the absence or presence of mislabeled data
01 Dec 2021-Vol. 2, Iss: 4, pp 043001
About: The article was published on 2021-12-01 and is currently open access. It has received 10 citations till now. The article focuses on the topics: Artificial neural network.
Citations
More filters
TL;DR: In this article , a comparative analysis is carried out to determine the most appropriate Artificial Intelligence methods to forecast photovoltaic production in buildings, including Random Forest (RF), Extreme Gradient Boost (XGBoost), and Support Vector Regressor (SVR).
Abstract: The increasing trend in energy demand is higher than the one from renewable generation, in the coming years. One of the greatest sources of consumption are buildings. The energy management of a building by means of the production of photovoltaic energy in situ is a common alternative to improve sustainability in this sector. An efficient trade-off of the photovoltaic source in the fields of Zero Energy Buildings (ZEB), nearly Zero Energy Buildings (nZEB) or MicroGrids (MG) requires an accurate forecast of photovoltaic production. These systems constantly generate data that are not used. Artificial Intelligence methods can take advantage of this missing information and provide accurate forecasts in real time. Thus, in this manuscript a comparative analysis is carried out to determine the most appropriate Artificial Intelligence methods to forecast photovoltaic production in buildings. On the one hand, the Machine Learning methods considered are Random Forest (RF), Extreme Gradient Boost (XGBoost), and Support Vector Regressor (SVR). On the other hand, Deep Learning techniques used are Standard Neural Network (SNN), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN). The models are checked with data from a real building. The models are validated using normalized Mean Bias Error (nMBE), normalized Root Mean Squared Error (nRMSE), and the coefficient of variation (R2). Standard deviation is also used in conjunction with these metrics. The results show that the models forecast the test set with errors of less than 2.00% (nMBE) and 7.50% (nRMSE) in the case of considering nights, and 4.00% (nMBE) and 11.50% (nRMSE) if nights are not considered. In both situations, the R2 is greater than 0.85 in all models.
5 citations
02 Mar 2023
TL;DR: In this article , a U-shaped generalization curve was observed in Mixup training, where the performance of Mixup-trained models starts to decay after training for a large number of epochs.
Abstract: Mixup, which creates synthetic training instances by linearly interpolating random sample pairs, is a simple and yet effective regularization technique to boost the performance of deep models trained with SGD. In this work, we report a previously unobserved phenomenon in Mixup training: on a number of standard datasets, the performance of Mixup-trained models starts to decay after training for a large number of epochs, giving rise to a U-shaped generalization curve. This behavior is further aggravated when the size of original dataset is reduced. To help understand such a behavior of Mixup, we show theoretically that Mixup training may introduce undesired data-dependent label noises to the synthesized data. Via analyzing a least-square regression problem with a random feature model, we explain why noisy labels may cause the U-shaped curve to occur: Mixup improves generalization through fitting the clean patterns at the early training stage, but as training progresses, Mixup becomes over-fitting to the noise in the synthetic data. Extensive experiments are performed on a variety of benchmark datasets, validating this explanation.
4 citations
TL;DR: The Fokker-Planck equation of the underlying stochastic learning dynamics is solved and it is found that the additional landscape-dependent SGD-loss breaks the degeneracy and serves as an effective regularization for finding flat solutions.
Abstract: Generalization is one of the most important problems in deep learning, where there exist many low-loss solutions due to overparametrization. Previous empirical studies showed a strong correlation between flatness of the loss landscape at a solution and its generalizability, and stochastic gradient descent (SGD) is crucial in finding the flat solutions. To understand the effects of SGD, we construct a simple model whose overall loss landscape has a continuous set of degenerate (or near-degenerate) minima and the loss landscape for a minibatch is approximated by a random shift of the overall loss function. By direct simulations of the stochastic learning dynamics and solving the underlying Fokker-Planck equation, we show that due to its strong anisotropy the SGD noise introduces an additional effective loss term that decreases with flatness and has an overall strength that increases with the learning rate and batch-to-batch variation. We find that the additional landscape-dependent SGD loss breaks the degeneracy and serves as an effective regularization for finding flat solutions. As a result, the flatness of the overall loss landscape increases during learning and reaches a higher value (flatter minimum) for a larger SGD noise strength before the noise strength reaches a critical value when the system fails to converge. These results, which are verified in realistic neural network models, elucidate the role of SGD for generalization, and they may also have important implications for hyperparameter selection for learning efficiently without divergence.
2 citations
TL;DR: The results provide an unified framework, which will reveal how different regularization schemes (weight decay, stochastic gradient descent with different batch sizes and learning rates, dropout), training data size, and labeling noise affect generalization performance by controlling either one or both of these two geometric determinants for generalization.
Abstract: One of the fundamental problems in machine learning is generalization. In neural network models with a large number of weights (parameters), many solutions can be found to fit the training data equally well. The key question is which solution can describe testing data not in the training set. Here, we report the discovery of an exact duality (equivalence) between changes in activities in a given layer of neurons and changes in weights that connect to the next layer of neurons in a densely connected layer in any feed forward neural network. The activity-weight (A-W) duality allows us to map variations in inputs (data) to variations of the corresponding dual weights. By using this mapping, we show that the generalization loss can be decomposed into a sum of contributions from different eigen-directions of the Hessian matrix of the loss function at the solution in weight space. The contribution from a given eigendirection is the product of two geometric factors (determinants): the sharpness of the loss landscape and the standard deviation of the dual weights, which is found to scale with the weight norm of the solution. Our results provide an unified framework, which we used to reveal how different regularization schemes (weight decay, stochastic gradient descent with different batch sizes and learning rates, dropout), training data size, and labeling noise affect generalization performance by controlling either one or both of these two geometric determinants for generalization. These insights can be used to guide development of algorithms for finding more generalizable solutions in overparametrized neural networks.
1 citations
Journal Article•
TL;DR: A novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training is proposed, built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections.
Abstract: Efficient model selection for identifying a suitable pre-trained neural network to a downstream task is a fundamental yet challenging task in deep learning. Current practice requires expensive computational costs in model training for performance prediction. In this paper, we propose a novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training. Our framework is built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections. Therefore, a converged neural network is associated with an equilibrium state of a networked system composed of those edges. To this end, we construct a network mapping φ, converting a neural network GA to a directed line graph GB that is defined on those edges in GA. Next, we derive a neural capacitance metric βeff as a predictive measure universally capturing the generalization capability of GA on the downstream task using only a handful of early training results. We carried out extensive experiments using 17 popular pre-trained ImageNet models and five benchmark datasets, including CIFAR10, CIFAR100, SVHN, Fashion MNIST and Birds, to evaluate the fine-tuning performance of our framework. Our neural capacitance metric is shown to be a powerful indicator for model selection based only on early training results and is more efficient than state-of-the-art methods.
1 citations
References
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
[...]
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
46,982 citations
Book•
[...]
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.
38,208 citations
TL;DR: Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.
Abstract: The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.
14,377 citations
TL;DR: In this article, a method for making successive experiments at levels x1, x2, ··· in such a way that xn will tend to θ in probability is presented.
Abstract: Let M(x) denote the expected value at level x of the response to a certain experiment. M(x) is assumed to be a monotone function of x but is unknown to the experimenter, and it is desired to find the solution x = θ of the equation M(x) = α, where a is a given constant. We give a method for making successive experiments at levels x1, x2, ··· in such a way that xn will tend to θ in probability.
9,312 citations