Abstract reasoning refers to the ability to analyze information, discover rules at an intangible level, and solve problems in innovative ways. Raven's Progressive Matrices (RPM) test is typically used to examine the capability of abstract reasoning. In the test, the subject is asked to identify the correct choice from the answer set to fill the missing panel at the bottom right of RPM (e.g., a 3$\times$3 matrix), following the underlying rules inside the matrix. Recent studies, taking advantage of Convolutional Neural Networks (CNNs), have achieved encouraging progress to accomplish the RPM test problems. Unfortunately, simply relying on the relation extraction at the matrix level, they fail to recognize the complex attribute patterns inside or across rows/columns of RPM. To address this problem, in this paper we propose a Hierarchical Rule Induction Network (HriNet), by intimating human induction strategies. HriNet extracts multiple granularity rule embeddings at different levels and integrates them through a gated embedding fusion module. We further introduce a rule similarity metric based on the embeddings, so that HriNet can not only be trained using a tuplet loss but also infer the best answer according to the similarity score. To comprehensively evaluate HriNet, we first fix the defects contained in the very recent RAVEN dataset and generate a new one named Balanced-RAVEN. Then extensive experiments are conducted on the large-scale dataset PGM and our Balanced-RAVEN, the results of which show that HriNet outperforms the state-of-the-art models by a large margin.

There are several real-world tasks that would benefit from applying multiagent reinforcement learning (MARL) algorithms, including the coordination among self-driving cars. The real world has challenging conditions for multiagent learning systems, such as its partial observable and nonstationary nature. Moreover, if agents must share a limited resource (e.g. network bandwidth) they must all learn how to coordinate resource use. This paper introduces a deep recurrent multiagent actor-critic framework (R-MADDPG) for handling multiagent coordination under partial observable set-tings and limited communication. We investigate recurrency effects on performance and communication use of a team of agents. We demonstrate that the resulting framework learns time dependencies for sharing missing observations, handling resource limitations, and developing different communication patterns among agents.

Harnham are partnered with a global retail business that brings in over $15 billion a year and uses machine learning for exciting uses like retail-robotics and chat-bots. Please register your interest by sending your CV to Elizabeth Sobel via the Apply link on this page.

Reinforcement learning is field that keeps growing and not only because of the breakthroughs in deep learning. Sure if we talk about deep reinforcement learning, it uses neural networks underneath, but there is more to it than that. In our journey through the world of reinforcement learning we focused on one of the most popular reinforcement learning algorithms out there Q-Learning. This approach is considered one of the biggest breakthroughs in Temporal Difference control. In this article, we are going to explore one variation and improvement of this algorithm – Double Q-Learning.

A guide showing how to train TensorFlow Lite object detection models and run them on Android, the Raspberry Pi, and more! TensorFlow Lite is an optimized framework for deploying lightweight deep learning models on resource-constrained edge devices. TensorFlow Lite models have faster inference time and require less processing power, so they can be used to obtain faster performance in realtime applications. This guide provides step-by-step instructions for how train a custom TensorFlow Object Detection model, convert it into an optimized format that can be used by TensorFlow Lite, and run it on Android phones or the Raspberry Pi. The guide is broken into three major portions. Each portion will have its own dedicated README file in this repository. This repository also contains Python code for running the newly converted TensorFlow Lite model to perform detection on images, videos, or webcam feeds. I used TensorFlow v1.13 while creating this guide, because TF v1.13 is a stable version that has great support from Anaconda. I will periodically update the guide to make sure it works with newer versions of TensorFlow.

Medical robots have demonstrated the ability to manipulate percutaneous instruments into soft tissue anatomy while working beyond the limits of human perception and dexterity. Robotic technologies further offer the promise of autonomy in carrying out critical tasks with minimal supervision when resources are limited. Here, we present a portable robotic device capable of introducing needles and catheters into deformable tissues such as blood vessels to draw blood or deliver fluids autonomously. Robotic cannulation is driven by predictions from a series of deep convolutional neural networks that encode spatiotemporal information from multimodal image sequences to guide real-time servoing. We demonstrate, through imaging and robotic tracking studies in volunteers, the ability of the device to segment, classify, localize and track peripheral vessels in the presence of anatomical variability and motion.

In modern text data analysis, NLP tools and NLP libraries are indispensable. Researchers and businesses use natural language processing tools to draw information from text data analysis. This analysis includes analyzing customer feedback, automating support systems, improving search and recommendation algorithms, and monitoring social media. There are a wide array of NLP tools and services available, and knowing their features is key to good results. While some tools are perfect for small projects, others are better for experts working on big data.

It seems that every year Google plans to shock the artificial intelligence(AI) world with new astonishing progress in natural language understanding(NLU) systems. Last year, the BERT model definitely stole the headlines of the NLU research space. Just a few weeks into 2020, Google Research published a new paper introducing Meena, a new deep learning model that can power chatbots that can engage in conversations about any domain. NLU has been one of the most active areas of research of the last few years and have produced some of the most widely adopted AI systems to date. However, despite all the progress, most conversational systems remain highly constrained to a specific domain which contrasts with our ability as humans to naturally converse about different topics.

Rice University engineers have developed a deep learning computer system that can accurately predict extreme weather events. Rice University engineers have developed a deep learning computer system that can accurately predict extreme weather events, like heatwaves, up to five days in advance using minimal information about current weather conditions. The new network uses an analog method of weather forecasting that computers made obsolete in the 1950s. The Phys.org website reported that the system was fed hundreds of maps that show surface temperatures and air pressures at five kilometers height, and each map shows those conditions several days apart. The new system is able to make five-day forecasts of extreme weather events like heat waves or winter storms with 85 percent accuracy, the German news agency reported.

Breast cancer has the highest mortality among cancers in women. Computer-aided pathology to analyze microscopic histopathology images for diagnosis with an increasing number of breast cancer patients can bring the cost and delays of diagnosis down. Deep learning in histopathology has attracted attention over the last decade of achieving state-of-the-art performance in classification and localization tasks. The convolutional neural network, a deep learning framework, provides remarkable results in tissue images analysis, but lacks in providing interpretation and reasoning behind the decisions. We aim to provide a better interpretation of classification results by providing localization on microscopic histopathology images. We frame the image classification problem as weakly supervised multiple instance learning problem where an image is collection of patches i.e. instances. Attention-based multiple instance learning (A-MIL) learns attention on the patches from the image to localize the malignant and normal regions in an image and use them to classify the image. We present classification and localization results on two publicly available BreakHIS and BACH dataset. The classification and visualization results are compared with other recent techniques. The proposed method achieves better localization results without compromising classification accuracy.