We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

/pdf/imagenet-classification-with-deep-convolutional-neural-1190x9a6b9.pdf

ImageNet Classification with Deep Convolutional Neural Networks

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

Data Mining - Concepts and Techniques.

Due to increasing concerns about global warming, greenhouse gas emissions, and the depletion of fossil fuels, the electric vehicles (EVs) receive massive popularity due to their performances and efficiencies in recent decades. EVs have already been widely accepted in the automotive industries considering the most promising replacements in reducing CO2 emissions and global environmental issues. Lithium-ion batteries have attained huge attention in EVs application due to their lucrative features such as lightweight, fast charging, high energy density, low self-discharge and long lifespan. This paper comprehensively reviews the lithium-ion battery state of charge (SOC) estimation and its management system towards the sustainable future EV applications. The significance of battery management system (BMS) employing lithium-ion batteries is presented, which can guarantee a reliable and safe operation and assess the battery SOC. The review identifies that the SOC is a crucial parameter as it signifies the remaining available energy in a battery that provides an idea about charging/discharging strategies and protect the battery from overcharging/over discharging. It is also observed that the SOC of the existing lithium-ion batteries have a good contribution to run the EVs safely and efficiently with their charging/discharging capabilities. However, they still have some challenges due to their complex electro-chemical reactions, performance degradation and lack of accuracy towards the enhancement of battery performance and life. The classification of the estimation methodologies to estimate SOC focusing with the estimation model/algorithm, benefits, drawbacks and estimation error are extensively reviewed. The review highlights many factors and challenges with possible recommendations for the development of BMS and estimation of SOC in next-generation EV applications. All the highlighted insights of this review will widen the increasing efforts towards the development of the advanced SOC estimation method and energy management system of lithium-ion battery for the future high-tech EV applications.

F. Sánchez Lasheras

Papers

Hybrid PSO–SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability

Battery state-of-charge estimator using the SVM technique

PM10 concentration forecasting in the metropolitan area of Oviedo (Northern Spain) using models based on SVM, MLP, VARMA and ARIMA: A case study.

Prediction of work-related accidents according to working conditions using support vector machines

Artificial neural networks applied to cancer detection in a breast screening programme