Service robots can help with many of our daily tasks, especially in those cases where it is inconvenient or unsafe for us to intervene - e.g., under extreme weather conditions or when social distance needs to be maintained. However, before we can successfully delegate complex tasks to robots, we need to enhance their ability to make sense of dynamic, real-world environments. In this context, the first prerequisite to improving the Visual Intelligence of a robot is building robust and reliable object recognition systems. While object recognition solutions are traditionally based on Machine Learning methods, augmenting them with knowledge-based reasoners has been shown to improve their performance. In particular, based on our prior work on identifying the epistemic requirements of Visual Intelligence, we hypothesise that knowledge of the typical size of objects could significantly improve the accuracy of an object recognition system. To verify this hypothesis, in this paper we present an approach to integrating knowledge about object sizes in a MLbased architecture. Our experiments in a real-world robotic scenario show that this combined approach ensures a significant performance increase over state-of-the-art Machine Learning methods.

As we deploy reinforcement learning agents to solve increasingly challenging problems, methods that allow us to inject prior knowledge about the structure of the world and effective solution strategies becomes increasingly important. In this work we consider how information and architectural constraints can be combined with ideas from the probabilistic modeling literature to learn behavior priors that capture the common movement and interaction patterns that are shared across a set of related tasks or contexts. For example the day-to day behavior of humans comprises distinctive locomotion and manipulation patterns that recur across many different situations and goals. We discuss how such behavior patterns can be captured using probabilistic trajectory models and how these can be integrated effectively into reinforcement learning schemes, e.g.\ to facilitate multi-task and transfer learning. We then extend these ideas to latent variable models and consider a formulation to learn hierarchical priors that capture different aspects of the behavior in reusable modules. We discuss how such latent variable formulations connect to related work on hierarchical reinforcement learning (HRL) and mutual information and curiosity based objectives, thereby offering an alternative perspective on existing ideas. We demonstrate the effectiveness of our framework by applying it to a range of simulated continuous control domains.

Cross-lingual Machine Reading Comprehension (CLMRC) remains a challenging problem due to the lack of large-scale annotated datasets in low-source languages, such as Arabic, Hindi, and Vietnamese. Many previous approaches use translation data by translating from a rich-source language, such as English, to low-source languages as auxiliary supervision. However, how to effectively leverage translation data and reduce the impact of noise introduced by translation remains onerous. In this paper, we tackle this challenge and enhance the cross-lingual transferring performance by a novel augmentation approach named Language Branch Machine Reading Comprehension (LBMRC). A language branch is a group of passages in one single language paired with questions in all target languages. We train multiple machine reading comprehension (MRC) models proficient in individual language based on LBMRC. Then, we devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages. Combining the LBMRC and multilingual distillation can be more robust to the data noises, therefore, improving the model's cross-lingual ability. Meanwhile, the produced single multilingual model is applicable to all target languages, which saves the cost of training, inference, and maintenance for multiple models. Extensive experiments on two CLMRC benchmarks clearly show the effectiveness of our proposed method.

Inspired by recent trends in vision and language learning, we explore applications of attention mechanisms for visio-lingual fusion within an application to story-based video understanding. Like other video-based QA tasks, video story understanding requires agents to grasp complex temporal dependencies. However, as it focuses on the narrative aspect of video it also requires understanding of the interactions between different characters, as well as their actions and their motivations. We propose a novel co-attentional transformer model to better capture long-term dependencies seen in visual stories such as dramas and measure its performance on the video question answering task. We evaluate our approach on the recently introduced DramaQA dataset which features character-centered video story understanding questions. Our model outperforms the baseline model by 8 percentage points overall, at least 4.95 and up to 12.8 percentage points on all difficulty levels and manages to beat the winner of the DramaQA challenge.

As a data scientist, you'll have to extract useful information from extremely imperfect data. You can't completely eliminate uncertainty but you can reduce it with a strong grasp of statistics and probability fundamentals.

I have always emphasized on the importance of mathematics in machine learning. Here is a compilation of resources (books, videos, and papers) to get you going. This is not an exhaustive list but I have carefully curated it based on my experience and observations. This is a repost of my Twitter thread that you can find here. I will keep updating the list here as I come across more useful resources.

Robotic Drives & Physics: Robotics, learn by building III Just in time for Black Friday, this course is being uploaded as you read this! Main lessons will be posted over the months of November and December. Description Please note: Content is being uploaded through November/December. This is a new course. Building on the knowledge you gained in the Analog Electronics and Digital Electronics modules, you'll open even more doors to diverse careers and hobbies by learning how to physically move robots and mechatronics. Robotic drives and physics are intimately intertwined - almost the same topic in fact.

Introduction & Scope: Global Data Science and Machine Learning Service Market This in-depth research offering entailing key developments in …

It has been known for centuries that many fish swim in schools, with large groups moving in unison. But scientists have never fully known why, and have been unable to prove how this behaviour benefits them. Now, European researchers have used robotic fish to show it it is up to 13.5 per cent more efficient for fish to swim in a group than alone, allowing them to save energy. This had been the long-standing theory, but it had never been conclusively proven. European researchers used robotic fish to prove it is because they allow fish to save energy and up to 13.5 per cent more efficient than swimming alone Scientists from the Max Planck Institute of Animal Behavior (MPI-AB), the University of Konstanz, and Peking University, set about building a lifelike robot to test the hypothesis.

Our food industry media channels - What's New in Food Technology & Manufacturing magazine and the Food Processing website - provide busy food manufacturing, packaging and design professionals with an easy-to-use, readily available source of information that is crucial to gaining valuable industry insight. Members have access to thousands of informative items across a range of media channels. Membership is FREE to qualified industry professionals across Australia.