scispace - formally typeset
Search or ask a question
Author

Andrew Y. Ng

Other affiliations: Max Planck Society, Baidu, Carnegie Mellon University  ...read more
Bio: Andrew Y. Ng is an academic researcher from Stanford University. The author has contributed to research in topics: Deep learning & Supervised learning. The author has an hindex of 130, co-authored 345 publications receiving 164995 citations. Previous affiliations of Andrew Y. Ng include Max Planck Society & Baidu.


Papers
More filters
Posted Content
TL;DR: In this article, the structural transformation processes for face-centered cubic (FCC) gold under shock compressions have been unambiguously revealed from the atomic level, and the sequence of structures, stacking faults, body centered cubic (BCC) phase, and coexistence of BCC-amorphous phase is confirmed.
Abstract: The microscopic mechanism of dynamic phase transition of noble metals is much demanding and challenging with the development of in situ x-ray diffraction measurements [Phys. Rev. Lett. 124, 235701 (2020); Phys. Rev. Lett. 123, 045702 (2019); Phys. Rev. Lett. 123, 045701 (2019)]. Through rapid compression like shock impact, gold exhibits unique structural transformation characteristics, in which the previous theoretical results are far away from the experiments. In order to simulate the complex process, we construct an interaction potential by training a deep neural network with a set of ab initio calculations. By using molecular dynamics simulations, the structural transformation processes for face-centered cubic (FCC) gold under shock compressions have been unambiguously revealed from the atomic level. In agreement with recent experiments, the sequence of structures, stacking faults, body-centered cubic (BCC) phase, and coexistence of BCC-amorphous phase are found until gold reaching completely melting up to 325 GPa, and a much lower transition pressure (113 GPa) to BCC phase is confirmed. Different from perfect BCC crystalline, the shock compression generates a BCC structure with many disorders, reducing the free energies and consequently largely lowering the transition pressure. Interestingly, by introducing defects in the initial FCC gold, it presents a reverse effect on the FCC-BCC phase transition. These defects in the form of collections of atoms give rise to the formation of the interface, leading to increasing interface barrier and reducing internal stress. Therefore, a competitive effect is highlighted between disorders and defects, determining the FCC-BCC phase transition threshold under dynamical compressions, which is absent in conventional understanding.

1 citations

Journal ArticleDOI
TL;DR: A random forest model performed the best among the five models and outperformed the existing debris warning system in Taiwan, suggesting the potential for machine learning models trained on hourly rainfall data alone to save lives while reducing false alerts.
Abstract: Taiwan has the highest susceptibility to and fatalities from debris flows worldwide. The existing debris flow warning system in Taiwan, which uses a time-weighted measure of rainfall, leads to alerts when the measure exceeds a predefined threshold. However, this system generates many false alarms and misses a substantial fraction of the actual debris flows. Towards improving this system, we implemented five machine learning models that input historical rainfall data and predict whether a debris flow will occur within a selected time. We found that a random forest model performed the best among the five models and outperformed the existing system in Taiwan. Furthermore, we identified the rainfall trajectories strongly related to debris flow occurrences and explored trade-offs between the risks of missing debris flows versus frequent false alerts. These results suggest the potential for machine learning models trained on hourly rainfall data alone to save lives while reducing false alerts. in a machine learning model.
Posted Content
TL;DR: In this paper, the authors compared three radiology report labelers: CheXpert, CheXbert, and VisualCheXbert on the task of extracting accurate chest X-ray image labels from radiology reports.
Abstract: Although deep learning models for chest X-ray interpretation are commonly trained on labels generated by automatic radiology report labelers, the impact of improvements in report labeling on the performance of chest X-ray classification models has not been systematically investigated. We first compare the CheXpert, CheXbert, and VisualCheXbert labelers on the task of extracting accurate chest X-ray image labels from radiology reports, reporting that the VisualCheXbert labeler outperforms the CheXpert and CheXbert labelers. Next, after training image classification models using labels generated from the different radiology report labelers on one of the largest datasets of chest X-rays, we show that an image classification model trained on labels from the VisualCheXbert labeler outperforms image classification models trained on labels from the CheXpert and CheXbert labelers. Our work suggests that recent improvements in radiology report labeling can translate to the development of higher performing chest X-ray classification models.
Journal ArticleDOI
TL;DR: A deep neural network model to predict prostate cancer on MRI that is trained on spatial coordinates and pathology of biopsy cores as ground truth is presented, which aims to eliminate the interobserver variability of radiologist interpretations and improve the detection of cancer in patients with false negative MRIs.

Cited by
More filters
Proceedings Article
01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

111,197 citations

Proceedings Article
03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which 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.
Abstract: 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.

73,978 citations

Proceedings Article
04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

55,235 citations

Proceedings Article
01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

49,914 citations

Proceedings ArticleDOI
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

40,257 citations