Harvard Medical school: Researchers from Harvard med school and Beth Israel Deaconess Medical Centre have developed AI powered systems to make pathological diagnosis more accurate by using deep learning and machine learning. The algorithm makes use of speech and image recognition to interpret pathological images and trains computers to differentiate between cancerous and non cancerous lesions. Combination of this algorithm with the pathologist's work led to a 99.5 percent accuracy rate.

Researchers at the Massachusetts Institute of Technology have developed an artificial intelligence (AI) system that can isolate small, nearly transparent imperfections in poorly lit images in order to reproduce objects. A blog post published by MIT News today describes a deep neural network -- layered mathematical functions loosely mimicking the behavior of neurons in the brain -- that can erase target artifacts from grainy images. George Barbastathis, professor of mechanical engineering at MIT, believes this might have applications in medicine. "In the lab, if you blast biological cells with light you burn them, and there is nothing left to image," he told MIT News. "When it comes to X-ray imaging, if you expose a patient to X-rays, you increase the danger they may get cancer. What we're doing here is -- you can get the same image quality but with a lower exposure to the patient. And in biology, you can reduce the damage to biological specimens when you want to sample them."

New neural network architectures and novel AI research papers come out every week from professors at universities, researchers at Google and other big tech firms, or even just developers with a strong interest in Deep Learning. Unfortunately for individuals who don't have a Ph.D. or robust fluency in back-propagation, linear algebra, or computational math, implementing these new Deep Learning techniques with no high-level API (like Keras) can be challenging and time-consuming. Thankfully, the Google Brain team recognizes these widespread problems in the AI community and subsequently created an open source library to help address these issues. Although Deep Learning isn't always the silver bullet people hope for in the Data Science world, it is a very useful tool for Natural Language Processing (NLP) task. For example, the use of word embeddings has revolutionized the effectiveness of language understanding techniques. I wanted to make an offline French to English translator for my team and our clients, using the best current techniques, which at the time was the Transformer architecture.

An Autoencoder is a deep learning neural network architecture that achieves state of the art performance in the area of collaborative filtering. In the first part of the article I will give you a theoretical overview and basic mathematics behind simple Autoencoders and their extension the Deep Autoencoders. In the second part we will dive in the practical stuff and I will show you how to implement this technique in TensorFlow step by step. In this article I will include and comment only the most important parts of the model. The whole model, the input pipeline and the preprocessing can be viewed in the corresponding GitHub repository.

Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distribution observations. Approximate Bayesian approaches are commonly used to estimate uncertainty for neural network predictions, but can struggle with out-of-distribution observations. Generative models can in principle detect out-of-distribution observations as those with a low estimated density. However, the mere presence of an out-of-distribution input does not by itself indicate an unsafe situation. In this paper, we present a method for uncertainty-aware robotic perception that combines generative modeling and model uncertainty to cope with uncertainty stemming from out-of-distribution states. Our method estimates an uncertainty measure about the model's prediction, taking into account an explicit (generative) model of the observation distribution to handle out-of-distribution inputs. This is accomplished by probabilistically projecting observations onto the training distribution, such that out-of-distribution inputs map to uncertain in-distribution observations, which in turn produce uncertain task-related predictions, but only if task-relevant parts of the image change. We evaluate our method on an action-conditioned collision prediction task with both simulated and real data, and demonstrate that our method of projecting out-of-distribution observations improves the performance of four standard Bayesian and non-Bayesian neural network approaches, offering more favorable trade-offs between the proportion of time a robot can remain autonomous and the proportion of impending crashes successfully avoided.

Millimeter Wave (MmWave) communication is one of the key technology of the fifth generation (5G) wireless systems to achieve the expected 1000x data rate. With large bandwidth at mmWave band, the link capacity between users and base stations (BS) can be much higher compared to sub-6GHz wireless systems. Meanwhile, due to the high cost of infrastructure upgrade, it would be difficult for operators to drastically enhance the capacity of backhaul links between mmWave BSs and the core network. As a result, the data rate provided by backhaul may not be sufficient to support all mmWave links, the backhaul connection becomes the new bottleneck that limits the system performance. On the other hand, as mmWave channels are subject to random blockage, the data rates of mmWave users significantly vary over time. With limited backhaul capacity and highly dynamic data rates of users, how to allocate backhaul resource to each user remains a challenge for mmWave systems. In this article, we present a deep reinforcement learning (DRL) approach to address this challenge. By learning the blockage pattern, the system dynamics can be captured and predicted, resulting in efficient utilization of backhaul resource. We begin with a discussion on DRL and its application in wireless systems. We then investigate the problem backhaul resource allocation and present the DRL based solution. Finally, we discuss open problems for future research and conclude this article.

In this paper we propose a method to model speaker and session variability and able to generate likelihood ratios using neural networks in an end-to-end phrase dependent speaker verification system. As in Joint Factor Analysis, the model uses tied hidden variables to model speaker and session variability and a MAP adaptation of some of the parameters of the model. In the training procedure our method jointly estimates the network parameters and the values of the speaker and channel hidden variables. This is done in a two-step backpropagation algorithm, first the network weights and factor loading matrices are updated and then the hidden variables, whose gradients are calculated by aggregating the corresponding speaker or session frames, since these hidden variables are tied. The last layer of the network is defined as a linear regression probabilistic model whose inputs are the previous layer outputs. This choice has the advantage that it produces likelihoods and additionally it can be adapted during the enrolment using MAP without the need of a gradient optimization. The decisions are made based on the ratio of the output likelihoods of two neural network models, speaker adapted and universal background model. The method was evaluated on the RSR2015 database.

Recent research about margin theory has proved that maximizing the minimum margin like support vector machines does not necessarily lead to better performance, and instead, it is crucial to optimize the margin distribution. In the meantime, margin theory has been used to explain the empirical success of deep network in recent studies. In this paper, we present mdNet (the Optimal Margin Distribution Network), a network which embeds a loss function in regard to the optimal margin distribution. We give a theoretical analysis of our method using the PAC-Bayesian framework, which confirms the significance of the margin distribution for classification within the framework of deep networks. In addition, empirical results show that the mdNet model always outperforms the baseline cross-entropy loss model consistently across different regularization situations. And our mdNet model also outperforms the cross-entropy loss (Xent), hinge loss and soft hinge loss model in generalization task through limited training data.

The popular approach is to constrain the reconstructions using compactness priors including sparsity. Several researchers have recently introduced off-the-grid continuous domain priors that are robust to discretization errors [1, 2], which provide significantly improved image quality in a range of applications. However, the main challenge is the significant increase in computational complexity. Recently, several researchers have introduced deep learning methodsas fast and efficient alternatives to compressed sensing algorithms. Current approaches can be categorized into direct and model based strategies. The direct approaches directly estimate the images from the undersampled measurements ortheir transforms/features [3, 4]. These methods learn to invert the forward operator over the space/manifold of images. Whilethis approach is more popular, a challenge with these schemes is the need to learn the inverse, which often requires large models (e.g.

Neural architecture search (NAS) enabled the discovery of state-of-the-art architectures in many domains. However, the success of NAS depends on the definition of the search space, i.e. the set of the possible to generate neural architectures. State-of-the-art search spaces are defined as a static sequence of decisions and a set of available actions for each decision, where each possible sequence of actions defines an architecture. We propose a more expressive formulation of NAS, using a graph search space. Our search space is defined as a graph where each decision is a vertex and each action is an edge. Thus the sequence of decisions defining an architecture is not fixed but is determined dynamically by the actions selected. The proposed approach allows to model iterative and branching aspects of the architecture design process. In this form, stronger priors about the search can be induced. We demonstrate in simulation basic iterative and branching search structures and show that using the graph representation improves sample efficiency.