Next Generation Automated Machine Learning (AML)

Automated Machine Learning has only been around for a little over two years and already there are over 20 providers in this space. However, a new European AML platform called Tazi, new in the US, is showing what the next generation of AML will look like.

Top 20 Deep Learning Papers, 2018 Edition

Deep Learning is constantly evolving at a fast pace. New techniques, tools and implementations are changing the field of Machine Learning and bringing excellent results.
1. Deep Learning, by Yann L., Yoshua B. & Geoffrey H. (2015) (Cited: 5,716)
2. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, by Martín A., Ashish A. B., Eugene B. C., et al. (2015) (Cited: 2,423)
3. TensorFlow: a system for large-scale machine learning, by Martín A., Paul B., Jianmin C., Zhifeng C., Andy D. et al. (2016) (Cited: 2,227)
4. Deep learning in neural networks, by Juergen Schmidhuber (2015) (Cited: 2,196)
5. Human-level control through deep reinforcement learning, by Volodymyr M., Koray K., David S., Andrei A. R., Joel V et al (2015) (Cited: 2,086)
6. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, by Shaoqing R., Kaiming H., Ross B. G. & Jian S. (2015) (Cited: 1,421)
7. Long-term recurrent convolutional networks for visual recognition and description, by Jeff D., Lisa Anne H., Sergio G., Marcus R., Subhashini V. et al. (2015) (Cited: 1,285)
8. MatConvNet: Convolutional Neural Networks for MATLAB, by Andrea Vedaldi & Karel Lenc (2015) (Cited: 1,148)
9. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, by Alec R., Luke M. & Soumith C. (2015) (Cited: 1,054)
10. U-Net: Convolutional Networks for Biomedical Image Segmentation, by Olaf R., Philipp F. &Thomas B. (2015) (Cited: 975)
11. Conditional Random Fields as Recurrent Neural Networks, by Shuai Z., Sadeep J., Bernardino R., Vibhav V. et al (2015) (Cited: 760)
12. Image Super-Resolution Using Deep Convolutional Networks, by Chao D., Chen C., Kaiming H. & Xiaoou T. (2014) (Cited: 591)
13. Beyond short snippets: Deep networks for video classification, by Joe Y. Ng, Matthew J. H., Sudheendra V., Oriol V., Rajat M. & George T. (2015) (Cited: 533)
14. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, by Christian S., Sergey I., Vincent V. & Alexander A A. (2017) (Cited: 520)
15. Salient Object Detection: A Discriminative Regional Feature Integration Approach, by Huaizu J., Jingdong W., Zejian Y., Yang W., Nanning Z. & Shipeng Li. (2013) (Cited: 518)
16. Visual Madlibs: Fill in the Blank Description Generation and Question Answering, by Licheng Y., Eunbyung P., Alexander C. B. & Tamara L. B. (2015) (Cited: 510)
17. Asynchronous methods for deep reinforcement learning, by Volodymyr M., Adrià P. B., Mehdi M., Alex G., Tim H. et al. (2016) (Cited: 472)
18. Theano: A Python framework for fast computation of mathematical expressions., by by Rami A., Guillaume A., Amjad A., Christof A. et al (2016) (Cited: 451)
19. Deep Learning Face Attributes in the Wild, by Ziwei L., Ping L., Xiaogang W. & Xiaoou T. (2015) (Cited: 401)
20. Character-level convolutional networks for text classification, by Xiang Z., Junbo Jake Z. & Yann L. (2015) (Cited: 401)

How To Choose The Right Chart Type For Your Data

Data speaks best through visuals, not words – so believes renowned data journalist and TEDtalks speaker, David McCandless. According to him, 80% of all that we learn gets imbibed visually, and research would have to agree. Three groups of economists participated in a study where they were given a dataset and asked everyone the same question. Of the group armed with only the data and standard statistical analysis, 72% got the answer wrong. Another was provided the data, the analysis, and a chart as well – errors dropped to 61%. But (and here’s the catch) the final group had only the go-to chart. And only 3% answered incorrectly! The power of charts to aid accurate interpretation is, to put it plainly, mindblowing. That’s why users across the globe are increasingly looking at charts (or graphs) and pictorial representations to maximize the information at hand.

How companies around the world apply machine learning

Strata Data London will introduce technologies and techniques; showcase use cases; and highlight the importance of ethics, privacy, and security.

RStudio GPU Workstations in the Cloud with Paperspace

We are very pleased to announce the availability of an RStudio TensorFlow template for the Paperspace cloud desktop service. If you don’t have local access to a modern NVIDIA GPU, your best bet is typically to run GPU intensive training jobs in the cloud. Paperspace is a cloud service that provides access to a fully preconfigured Ubuntu 16.04 desktop environment equipped with a GPU. With the addition of the RStudio TensorFlow template you can now provision a ready to use RStudio TensorFlow w/ GPU workstation in just a few clicks.

Performance: Avoid Coercing Indices To Doubles

x[idxs + 1] or x[idxs + 1L]? That is the question.