Deep learning shows great potential for the domain of digital pathology. An automated digital pathology system could serve as a second reader, perform initial triage in large screening studies, or assist in reporting. However, it is expensive to exhaustively annotate large histology image databases, since medical specialists are a scarce resource. In this paper, we apply the semi-supervised teacher-student knowledge distillation technique proposed by Yalniz et al. (2019) to the task of quantifying prognostic features in colorectal cancer. We obtain accuracy improvements through extending this approach to a chain of students, where each student's predictions are used to train the next student i.e. the student becomes the teacher. Using the chain approach, and only 0.5% labelled data (the remaining 99.5% in the unlabelled pool), we match the accuracy of training on 100% labelled data. At lower percentages of labelled data, similar gains in accuracy are seen, allowing some recovery of accuracy even from a poor initial choice of labelled training set. In conclusion, this approach shows promise for reducing the annotation burden, thus increasing the affordability of automated digital pathology systems.

Being able to infer the goal of people we observe, interact with, or read stories about is one of the hallmarks of human intelligence. A prominent idea in current goal-recognition research is to infer the likelihood of an agent's goal from the estimations of the costs of plans to the different goals the agent might have. Different approaches implement this idea by relying only on handcrafted symbolic representations. Their application to real-world settings is, however, quite limited, mainly because extracting rules for the factors that influence goal-oriented behaviors remains a complicated task. In this paper, we introduce a novel idea of using a symbolic planner to compute plan-cost insights, which augment a deep neural network with an imagination capability, leading to improved goal recognition accuracy in real and synthetic domains compared to a symbolic recognizer or a deep-learning goal recognizer alone.

Real world navigation requires robots to operate in unfamiliar, dynamic environments, sharing spaces with humans. Navigating around humans is especially difficult because it requires predicting their future motion, which can be quite challenging. We propose a novel framework for navigation around humans which combines learning-based perception with model-based optimal control. Specifically, we train a Convolutional Neural Network (CNN)-based perception module which maps the robot's visual inputs to a waypoint, or next desired state. This waypoint is then input into planning and control modules which convey the robot safely and efficiently to the goal. To train the CNN we contribute a photo-realistic bench-marking dataset for autonomous robot navigation in the presence of humans. The CNN is trained using supervised learning on images rendered from our photo-realistic dataset. The proposed framework learns to anticipate and react to peoples' motion based only on a monocular RGB image, without explicitly predicting future human motion. Our method generalizes well to unseen buildings and humans in both simulation and real world environments. Furthermore, our experiments demonstrate that combining model-based control and learning leads to better and more data-efficient navigational behaviors as compared to a purely learning based approach. Videos describing our approach and experiments are available on the project website.

Intent and Slot Identification are two important tasks in Spoken Language Understanding (SLU). For a natural language utterance, there is a high correlation between these two tasks. A lot of work has been done on each of these using Recurrent-Neural-Networks (RNN), Convolution Neural Networks (CNN) and Attention based models. Most of the past work used two separate models for intent and slot prediction. Some of them also used sequence-to-sequence type models where slots are predicted after evaluating the utterance-level intent. In this work, we propose a parallel Intent and Slot Prediction technique where separate Bidirectional Gated Recurrent Units (GRU) are used for each task. We posit the usage of MLB (Multimodal Low-rank Bilinear Attention Network) fusion for improvement in performance of intent and slot learning. To the best of our knowledge, this is the first attempt of using such a technique on text based problems. Also, our proposed methods outperform the existing state-of-the-art results for both intent and slot prediction on two benchmark datasets

We present a mixture model whose components are Restricted Boltzmann Machines (RBMs). This possibility has not been considered before because computing the partition function of an RBM is intractable, which appears to make learning a mixture of RBMs intractable as well. Surprisingly, when formulated as a third-order Boltzmann machine, such a mixture model can be learned tractably using contrastive divergence. The energy function of the model captures three-way interactions among visible units, hidden units, and a single hidden multinomial unit that represents the cluster labels. The distinguishing feature of this model is that, unlike other mixture models, the mixing proportions are not explicitly parameterized.

Artificial Intelligence with TensorFlow is a four-week, part time, online training course that offers an introduction to neural networks, deep learning, machine learning, artificial intelligence and their many applications. This immersive, hands-on course teaches students the data science tools and techniques needed to build and test neural networks in TensorFlow using real-world data. This course is optimal for those who have taken Essential Data Tools & Practical Machine Learning and desire to expand their knowledge of modeling and data science with TensorFlow.

In a paper published on the preprint server Arxiv.org, Besides addressing the task of visual classification, StarNet supports the task of weakly supervised few-shot object detection, such that only a small amount of noisy data is required to achieve reasonable accuracy with it. StarNet could increase transparency in and reduce the amount of training data needed for new visual domains, like self-driving cars and autonomous industrial robots. By extension, it could cut down on deployment time for AI projects involving classifiers, which surveys show ranges between 8 and 90 days. StarNet consists of a few-shot classifier module attached to an extractor, both of which are trained in a meta-learning fashion where episodes are randomly sampled from classes.

One of the most foundational building blocks of any modern autonomous system is the perception module. This helps any machine interpret information from the real world through sensors such as cameras, lidar and radars. In recent years, advances in deep learning have spawned an entirely new generation of perception algorithms that are developed by the huge amounts of data captured by these sensors. Deepen plays directly into this technology trend, providing AI-powered software tools and services that help process sensor data efficiently and accurately. Deepen helps companies curate, annotate and validate real-world, multi-sensor data for perception development.

If you have a relative working in the banking industry, ask the person what annoys him/her most about the job. You will surely receive an answer that is related to the task of data entry i.e. the practice of manually entering serial numbers and names from financial documents into the bank's database. It might interest your relative to know that the entire process of data entry can be automated. HOW! he or she might ask. Nanonets supports data extraction from all major financial documents.

Protein is of utmost importance in the human body. It is considered as the building blocks of life. Scientists, for a long, have been studying its properties and functionalities in order to improve proteins and design completely new proteins that perform new functions and processes. Recently, an innovation came into being when researchers in the United States and Taiwan explored how to create new proteins by using machine learning to translate protein structures into musical scores, presenting an unusual way to translate physics concepts across disparate domains, noted APL Bioengineering. A deep learning model has been employed to design de novo proteins, based on the interplay of elementary building blocks via hierarchical patterns.