Thoracic diseases are very serious health problems that plague a large number of people. Chest X-ray is currently one of the most popular methods to diagnose thoracic diseases, playing an important role in the healthcare workflow. However, reading the chest X-ray images and giving an accurate diagnosis remain challenging tasks for expert radiologists. With the success of deep learning in computer vision, a growing number of deep neural network architectures were applied to chest X-ray image classification. However, most of the previous deep neural network classifiers were based on deterministic architectures which are usually very noise-sensitive and are likely to aggravate the overfitting issue. In this paper, to make a deep architecture more robust to noise and to reduce overfitting, we propose using deep generative classifiers to automatically diagnose thorax diseases from the chest X-ray images. Unlike the traditional deterministic classifier, a deep generative classifier has a distribution middle layer in the deep neural network. A sampling layer then draws a random sample from the distribution layer and input it to the following layer for classification. The classifier is generative because the class label is generated from samples of a related distribution. Through training the model with a certain amount of randomness, the deep generative classifiers are expected to be robust to noise and can reduce overfitting and then achieve good performances. We implemented our deep generative classifiers based on a number of well-known deterministic neural network architectures, and tested our models on the chest X-ray14 dataset. The results demonstrated the superiority of deep generative classifiers compared with the corresponding deep deterministic classifiers.

The necessary and sufficient conditions for existence of a generalized representer theorem are presented for learning Hilbert space-valued functions. Representer theorems involving explicit basis functions and Reproducing Kernels are a common occurrence in various machine learning algorithms like generalized least squares, support vector machines, Gaussian process regression and kernel based deep neural networks to name a few. Due to the more general structure of the underlying variational problems, the theory is also relevant to other application areas like optimal control, signal processing and decision making. We present the generalized representer as a unified view for supervised and semi-supervised learning methods, using the theory of linear operators and subspace valued maps. The implications of the theorem are presented with examples of multi input-multi output regression, kernel based deep neural networks, stochastic regression and sparsity learning problems as being special cases in this unified view.

We present an effective technique for training deep learning agents capable of negotiating on a set of clauses in a contract agreement using a simple communication protocol. We use Multi Agent Reinforcement Learning to train both agents simultaneously as they negotiate with each other in the training environment. We also model selfish and prosocial behavior to varying degrees in these agents. Empirical evidence is provided showing consistency in agent behaviors. We further train a meta agent with a mixture of behaviors by learning an ensemble of different models using reinforcement learning. Finally, to ascertain the deployability of the negotiating agents, we conducted experiments pitting the trained agents against human players. Results demonstrate that the agents are able to hold their own against human players, often emerging as winners in the negotiation. Our experiments demonstrate that the meta agent is able to reasonably emulate human behavior.

While deep reinforcement learning (DRL) has led to numerous successes in recent years, reproducing these successes can be extremely challenging. One reproducibility challenge particularly relevant to DRL is nondeterminism in the training process, which can substantially affect the results. Motivated by this challenge, we study the positive impacts of deterministic implementations in eliminating nondeterminism in training. To do so, we consider the particular case of the deep Q-learning algorithm, for which we produce a deterministic implementation by identifying and controlling all sources of nondeterminism in the training process. One by one, we then allow individual sources of nondeterminism to affect our otherwise deterministic implementation, and measure the impact of each source on the variance in performance. We find that individual sources of nondeterminism can substantially impact the performance of agent, illustrating the benefits of deterministic implementations. In addition, we also discuss the important role of deterministic implementations in achieving exact replicability of results.

Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting. The architecture applies context level attention and incorporates additional external knowledge provided by descriptions of domain-specific words. It uses a bi-directional Gated Recurrent Unit (GRU) for encoding context and responses and learns to attend over the context words given the latent response representation and vice versa.In addition, it incorporates external domain specific information using another GRU for encoding the domain keyword descriptions. This allows better representation of domain-specific keywords in responses and hence improves the overall performance. Experimental results show that our model outperforms all other state-of-the-art methods for response selection in multi-turn conversations.

We propose a method for instance-level segmentation that uses RGB-D data as input and provides detailed information about the location, geometry and number of individual objects in the scene. This level of understanding is fundamental for autonomous robots. It enables safe and robust decision-making under the large uncertainty of the real-world. In our model, we propose to use the first and second order moments of the object occupancy function to represent an object instance. We train an hourglass Deep Neural Network (DNN) where each pixel in the output votes for the 3D position of the corresponding object center and for the object's size and pose. The final instance segmentation is achieved through clustering in the space of moments. The object-centric training loss is defined on the output of the clustering. Our method outperforms the state-of-the-art instance segmentation method on our synthesized dataset. We show that our method generalizes well on real-world data achieving visually better segmentation results.

Full stack Data Scientists are a dying breed A decade ago all Data Scientists were full stack Data Scientists. The field was new and they needed to be able to find and clean data, develop analytical models and present their results without the assistance of a team. Since that time Data Science has grown significantly, both in terms of technical complexity (e.g., deep learning) as well as demand from industry, academia, and government. Similar to how physicians have become increasing specialized, Data Scientists are now part of a broader team that includes Data Engineers, Deployment Engineers and AI specialists. The days of a lone Data Scientist making significant contributions are done.

We will see how to generate and plot fake data to get a better understanding of these concepts.

In a recent study, two researchers at the University of Washington used deep learning techniques to estimate obesity levels in 6 US cities. Adyasha Maharana and Dr. Elaine Okanyene Nsoesie used a convolutional neural network to extract information from Google Maps images which they found had a close relationship with obesity levels in the area. Features extracted by the convolutional neural network. The network seems to focus on natural features such as lakes and parks.Adyasha Maharana; Elaine Okanyene Nsoesie. The research suggests that the predictive power for obesity rates came from the presence of natural features such as lakes and parks detected by the neural network. The left side shows the true obesity rates from the Behavioral Risk Factor Surveillance System.

It wasn't that long ago that the idea of building technologies with'brains' that learn and are even structured just like ours seemed like science fiction. Just ask the distinguished speakers at the "Samsung AI Forum 2018". Held in Seoul from September 12th to 13th, the second edition of Samsung Electronics' artificial intelligence (AI) forum featured accomplished AI experts, who discussed how groundbreaking advancements are not only helping to create technology that will make our lives more comfortable, convenient and efficient. They're also teaching us more about how our own minds work. The forum began with a presentation from the founding director of the New York University Center for Data Science, and one of the world's leading minds in the field of deep learning, Yann LeCun.