Facebook has just short of 2.4 billion active users and sees 350 million photo uploads a day, plus more than 500,000 comments posted every minute. How do it track, monitor and gain value from this amount of information? "There are billions of users and no way for humans to scale to do the analytics," says Chirag Dekate, a research director covering artificial intelligence (AI), machine learning and deep learning at Gartner. So, Facebook uses learning systems and AI to scan posts. "No one can analyse every video or image, for banned speech or inflammatory material, or tag or for ad revenue generation," says Dekate.

Pathologists find tedious to examine the status of the sentinel lymph node on a large number of pathological scans. The examination process of such lymph node which encompasses metastasized cancer cells is histopathologically organized. However, the task of finding metastatic tissues is gradual which is often challenging. In this work, we present our deep convolutional neural network based model validated on PatchCamelyon (PCam) benchmark dataset for fundamental machine learning research in histopathology diagnosis. We find that our proposed model trained with a semi-supervised learning approach by using pseudo labels on PCam-level significantly leads to better performances to strong CNN baseline on the AUC metric.

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes that the expert is noisily optimal. Real people, on the other hand, often have systematic biases: risk-aversion, myopia, etc. One option is to try to characterize these biases and account for them explicitly during learning. But in the era of deep learning, a natural suggestion researchers make is to avoid mathematical models of human behavior that are fraught with specific assumptions, and instead use a purely data-driven approach. We decided to put this to the test -- rather than relying on assumptions about which specific bias the demonstrator has when planning, we instead learn the demonstrator's planning algorithm that they use to generate demonstrations, as a differentiable planner. Our exploration yielded mixed findings: on the one hand, learning the planner can lead to better reward inference than relying on the wrong assumption; on the other hand, this benefit is dwarfed by the loss we incur by going from an exact to a differentiable planner. This suggest that at least for the foreseeable future, agents need a middle ground between the flexibility of data-driven methods and the useful bias of known human biases. Code is available at https://tinyurl.com/learningbiases.

The emergence of one-shot approaches has greatly advanced the research on neural architecture search (NAS). Recent approaches train an over-parameterized super-network (one-shot model) and then sample and evaluate a number of sub-networks, which inherit weights from the one-shot model. The overall searching cost is significantly reduced as training is avoided for sub-networks. However, the network sampling process is casually treated and the inherited weights from an independently trained super-network perform sub-optimally for sub-networks. In this paper, we propose a novel one-shot NAS scheme to address the above issues. The key innovation is to explicitly estimate the joint a posteriori distribution over network architecture and weights, and sample networks for evaluation according to it. This brings two benefits. First, network sampling under the guidance of a posteriori probability is more efficient than conventional random or uniform sampling. Second, the network architecture and its weights are sampled as a pair to alleviate the sub-optimal weights problem. Note that estimating the joint a posteriori distribution is not a trivial problem. By adopting variational methods and introducing a hybrid network representation, we convert the distribution approximation problem into an end-to-end neural network training problem which is neatly approached by variational dropout. As a result, the proposed method reduces the number of sampled sub-networks by orders of magnitude. We validate our method on the fundamental image classification task. Results on Cifar-10, Cifar-100 and ImageNet show that our method strikes the best trade-off between precision and speed among NAS methods. On Cifar-10, we speed up the searching process by 20x and achieve a higher precision than the best network found by existing NAS methods.

In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify uncertainty in neural network models. However, as previously demonstrated, confidence estimates computed with a naive implementation of dropout can be poorly calibrated, particularly when using convolutional networks. In this paper, through the lens of ensemble learning, we associate calibration error with the correlation between the models sampled with dropout. Motivated by this, we explore the use of structured dropout to promote model diversity and improve confidence calibration. We use the SVHN, CIFAR-10 and CIFAR-100 datasets to empirically compare model diversity and confidence errors obtained using various dropout techniques. We also show the merit of structured dropout in a Bayesian active learning application.

This work tackles the problem of generating a medical report for multi-image panels. We apply our solution to the Renal Direct Immunofluorescence (RDIF) assay which requires a pathologist to generate a report based on observations across the eight different WSI in concert with existing clinical features. To this end, we propose a novel attention-based multi-modal generative recurrent neural network (RNN) architecture capable of dynamically sampling image data concurrently across the RDIF panel. The proposed methodology incorporates text from the clinical notes of the requesting physician to regulate the output of the network to align with the overall clinical context. In addition, we found the importance of regularizing the attention weights for word generation processes. This is because the system can ignore the attention mechanism by assigning equal weights for all members. Thus, we propose two regularizations which force the system to utilize the attention mechanism. Experiments on our novel collection of RDIF WSIs provided by a large clinical laboratory demonstrate that our framework offers significant improvements over existing methods.

Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. They interpret sensory data through a kind of machine perception, labeling or clustering raw input. The patterns they recognize are numerical, contained in vectors, into which all real-world data, be it images, sound, text or time series, must be translated. Neural networks help us cluster and classify. You can think of them as a clustering and classification layer on top of the data you store and manage.

In today's post, Neha Goel is going to share an overview about how you can use MATLAB and Simulink for Developing Artificial Intelligent components in your competitions. Neha joined the team recently and focuses on deep learning and data science competitions. Also find a section in this post where Neha reveals what projects she is currently working on. Competitions and students in different application areas are adding AI components to their projects. The major areas include Autonomous Vehicle Competitions, Aerospace, Robotics, Data Science etc. Refer to link here to know about all competitions MathWorks sponsors. Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) are some of the hottest topics right now.

In this talk, we will introduce deep learning and review some of the key advances in the field focusing on current attempts at a theoretical understanding. We will highlight today's most important ideas in the larger quest to demystify the blackbox.

Nvidia have announced that they've introduced a new Artificial Intelligence (AI) Deep Learning model that "aims to catapult the graphics industry into the AI Age," and the result is the first ever interactive AI rendered virtual world. In short, Nvidia now has an AI capable of rendering high definition virtual environments, that can be used to create Virtual Reality (VR) games and simulations, in real time, and that's big because it takes the effort and cost out of having to design and make them from scratch, which has all sorts of advantages. In order to work their magic the researchers used what they called a Conditional Generative Neural Network as a starting point and then trained a neural network to render new 3D environments, and now the breakthrough will allow developers and artists of all kinds to create new interactive 3D virtual worlds based on videos from the real world, dramatically lowering the cost and time it takes to create virtual worlds. "NVIDIA has been creating new ways to generate interactive graphics for 25 years – and this is the first time we can do this with a neural network," said the leader of the Nvidia researchers Bryan Catanzaro, Vice President of Applied Deep Learning at Nvidia. "Neural networks – specifically – generative models like these are going to change the way graphics are created."