Explore how deep learning will impact healthcare, manufacturing, search & transportation. Where do the challenges still lie in research and application? Learn from & connect with 900 industry innovators sharing best practices to advance the smart artificial intelligence revolution.

Country: USA Funding: $15 m Enlitic applies the state-of-the-art in deep learning technology to medicine. Deep learning is loosely based on how the human brain works and has unleashed colossal capabilities in computer vision, language translation, and speech recognition. Our team of healthcare executives, physicians, and data science experts are adapting deep learning to medicine, with the goal of bringing patients radically improved diagnostic outcomes. We collaborate closely with medical centers to validate our technology and benchmark our performance against publicly available medical data sets.

Release newest version code, which fix some previous issues and also add support for new backbones and multi-gpu training. This is a PyTorch(0.4.1) implementation of DeepLab-V3-Plus. It can use Modified Aligned Xception and ResNet as backbone. Currently, we train DeepLab V3 Plus using Pascal VOC 2012, SBD and Cityscapes datasets. The code was tested with Anaconda and Python 3.6. For PyTorch dependency, see pytorch.org for more details.

The accuracy of automatic speech recognition has made significant gains in the last few years thanks to the advent of deep neural networks. But there's one area that has thwarted researchers: telling multiple speakers apart. Now a startup called Chorus says it has made a breakthrough in the matter through a technique it calls "voice fingerprinting." Speech recognition and computer vision arguably are the two computational challenges that have benefited the most from deep learning. Armed with huge training sets – including vast troves of photographs and digital recordings of voices – convolutional neural network (CNNs) and recurrent neural networks (RNNs) have given computers sensory perception that can almost rival humans' senses.

Weight constraints provide an approach to reduce the overfitting of a deep learning neural network model on the training data and improve the performance of the model on new data, such as the holdout test set. There are multiple types of weight constraints, such as maximum and unit vector norms, and some require a hyperparameter that must be configured. In this tutorial, you will discover the Keras API for adding weight constraints to deep learning neural network models to reduce overfitting. How to Reduce Overfitting in Deep Neural Networks With Weight Constraints in Keras Photo by Ian Sane, some rights reserved. The Keras API supports weight constraints.

If you remember anything from Calculus (not a trivial feat), it might have something to do with optimization. Finding the best numerical solution to a given problem is an important part of many branches in mathematics, and Machine Learning is no exception. Optimizers, combined with their cousin the Loss Function, are the key pieces that enable Machine Learning to work for your data. This post will walk you through the optimization process in Machine Learning, how loss functions fit into the equation (no pun intended), and some popular approaches. We'll also include some resources for further reading and experimentation.

Deep learning has revolutionized the ability to learn "end-to-end" autonomous vehicle control directly from raw sensory data. While there have been recent advances on extensions to handle forms of navigation instruction, these works are unable to capture the full distribution of possible actions that could be taken and to reason about localization of the robot within the environment. In this paper, we extend end-to-end driving networks with the ability to understand maps. We define a novel variational network capable of learning from raw camera data of the environment as well as higher level roadmaps to predict (1) a full probability distribution over the possible control commands; and (2) a deterministic control command capable of navigating on the route specified within the map. Additionally, we formulate how our model can be used to localize the robot according to correspondences between the map and the observed visual road topology, inspired by the rough localization that human drivers can perform. We evaluate our algorithms on real-world driving data, and reason about the robustness of the inferred steering commands under various types of rich driving scenarios. In addition, we evaluate our localization algorithm over a new set of roads and intersections which the model has never driven through and demonstrate rough localization in situations without any GPS prior.

The ability to precisely quantify similarity between various entities has been a fundamental complication in various problem spaces specifically in the classification of cellular images. Contemporary similarity measures applied in the domain of image processing proposed by the scientific community are mainly pursued in supervised settings. In this work, we will explore the innovative algorithmic normalized compression distance metric based on the information theoretic concept of Kolmogorov Complexity. Additionally we will observe its possible implementation in Convolutional Neural Networks to facilitate and automate the classification of Retinal Pigment Epithelial cell cultures for use in Age Related Macular Degeneration Stem Cell therapy in an unsupervised setting.

Previous studies have shown that deep neural networks (DNNs) with common settings often capture target functions from low to high frequency, which is called Frequency Principle (F-Principle). It has also been shown that F-Principle can provide an understanding to the often observed good generalization ability of DNNs. However, previous studies focused on the loss function of mean square error, while various loss functions are used in practice. In this work, we show that the F-Principle holds for a general loss function (e.g., mean square error, cross entropy, etc.). In addition, DNN's F-Principle may be applied to develop numerical schemes for solving various problems which would benefit from a fast converging of low frequency. As an example of the potential usage of F-Principle, we apply DNN in solving differential equations, in which conventional methods (e.g., Jacobi method) is usually slow in solving problems due to the convergence from high to low frequency.

How to effectively address the domain adaptation problem is a challenging task for person re-identification (reID). In this work, we make the first endeavour to tackle this issue according to one shot learning. Given an annotated source training set and a target training set that only one instance for each category is annotated, we aim to achieve competitive re-ID performance on the testing set of the target domain. To this end, we introduce a similarity-guided strategy to progressively assign pseudo labels to unlabeled instances with different confidence scores, which are in turn leveraged as weights to guide the optimization as training goes on. Collaborating with a simple self-mining operation, we make significant improvement in the domain adaptation tasks of re-ID. In particular, we achieve the mAP of 71.5% in the adaptation task of DukeMTMC-reID to Market1501 with one shot setting, which outperforms the state-of-arts of unsupervised domain adaptation more than 17.8%. Under the five shots setting, we achieve competitive accuracy of the fully supervised setting on Market-1501. Code will be made available.