Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified framework for the tasks of referring expression comprehension and generation. Our model is composed of three modules: speaker, listener, and reinforcer . The speaker generates referring expressions, the listener comprehends referring expressions, and the reinforcer introduces a reward function to guide sampling of more discriminative expressions. The listener-speaker modules are trained jointly in an end-to-end learning framework, allowing the modules to be aware of one another during learning while also benefiting from the discriminative reinforcer's feedback. W e demonstrate that this unified framework and training achieves state-of-the-art results for both comprehension and generation on three referring expression datasets. Project and demo page: https://vision.cs.unc.edu/refer.

We describe a system to detect objects in three-dimensional space using video and inertial sensors (accelerometer and gyrometer), ubiquitous in modern mobile platforms from phones to drones. Inertials afford the ability to impose class-specific scale priors for objects, and provide a global orientation reference. A minimal sufficient representation, the posterior of semantic (identity) and syntactic (pose) attributes of objects in space, can be decomposed into a geometric term, which can be maintained by a localization-and-mapping filter, and a likelihood function, which can be approximated by a discriminatively-trained convolutional neural network. The resulting system can process the video stream causally in real time, and provides a representation of objects in the scene that is persistent: Confidence in the presence of objects grows with evidence, and objects previously seen are kept in memory even when temporarily occluded, with their return into view automatically predicted to prime re-detection.

Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent should be able to avoid negative transfer, which happens when the transfer hampers or slows down the learning instead of helping it. Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task. We propose A2T (Attend, Adapt and Transfer), an attentive deep architecture which adapts and transfers from these source tasks. Our model is generic enough to effect transfer of either policies or value functions. Empirical evaluations on different learning algorithms show that A2T is an effective architecture for transfer by being able to avoid negative transfer while transferring selectively from multiple source tasks in the same domain.

The tech world has embraced Machine Learning (ML) for its powerful intuitive capabilities--to increase click-through rates on ads, sell more books, and help you keep in touch with mom. Despite being increasingly common as a classification tool in applications ranging from transcriptomics, metabolomics, and neuronal synaptic activities, ML is still almost absent in the area of bioengineering. Why is that and what can we do to increase ML use in bioengineering? Machine Learning algorithms that date back half a century are now commonly used for pattern-based analysis, including Decision Trees, Nearest Neighbors, Neural Nets, and more recently with significant success Deep Learning--a version of Neural Net with more layers and more nodes--received significant attention when it won against the best human in the ancient Chinese game of Go. Deep Learning has been enabled by access to new powerful computational hardware, in particular the graphical processing units (GPUs) originally developed for the gaming industry. These gaming GPUs allow for massively parallel computations, which is perfect for ML applications.

We provide a deep learning platform for optimized analysis and interpretation of radiologic and ultrasound imaging.

In this paper, we present a robotic prediction agent including a darkforest Go engine, a fuzzy markup language (FML) assessment engine, an FML-based decision support engine, and a robot engine for game of Go application. The knowledge base and rule base of FML assessment engine are constructed by referring the information from the darkforest Go engine located in NUTN and OPU, for example, the number of MCTS simulations and winning rate prediction. The proposed robotic prediction agent first retrieves the database of Go competition website, and then the FML assessment engine infers the winning possibility based on the information generated by darkforest Go engine. The FML-based decision support engine computes the winning possibility based on the partial game situation inferred by FML assessment engine. Finally, the robot engine combines with the human-friendly robot partner PALRO, produced by Fujisoft incorporated, to report the game situation to human Go players. Experimental results show that the FML-based prediction agent can work effectively.

Last year, a strange self-driving car was released onto the quiet roads of Monmouth County, New Jersey. The experimental vehicle, developed by researchers at the chip maker Nvidia, didn't look different from other autonomous cars, but it was unlike anything demonstrated by Google, Tesla, or General Motors, and it showed the rising power of artificial intelligence. The car didn't follow a single instruction provided by an engineer or programmer. Instead, it relied entirely on an algorithm that had taught itself to drive by watching a human do it. Getting a car to drive this way was an impressive feat. But it's also a bit unsettling, since it isn't completely clear how the car makes its decisions.

Billions of neurons in our brain are wired together in a sophisticated manner to give us the amazing ability of learning all sort of things. Artificial Neural Networks (ANNs) were proposed more than six decades ago (precisely in 1943) in an attempt to develop intelligent algorithms that can mimic the fascinating capabilities of the visual cortex part of human brain in making sense of the external world around us. Up until the last few years, all ANN based solutions were too simple, in terms of their structures and the total number of neurons, to tackle complex real-life problems such as biometric recognition. In fact, building complex and'deep' ANN was not easily feasible for two key reasons: the lack of computation powers and the limited availability of training data. The introduction of powerful and affordable GPUs for training ANN in recent years along with the availability of large volume of labelled data has led to the emergence of Deep Learning as a state-of-art machine learning approach.

The rapidly approaching reality of driverless vehicles has the potential to revolutionize the way we move people and goods from place to place. Entire industries face disruption, while others, like space exploration, are just getting started. In this video, Matt Coatney discusses the limitations of previous AI technologies and explains how modern deep learning has advanced intelligently automated systems. Whether you are an executive, manager, or an entrepreneur, this video will help you imagine further applications of deep learning in other industries ranging from factory automation to toys. Sign up for Safari now and get 10 days of free access to The Business of Deep Learning and more.

Previous lists have included both general purpose and specialized machine learning and deep learning libraries, along with auxiliary support, data cleaning, and automation tools. This time around we showcase 5 more machine learning-related projects which you may not yet heard of, including those from across a number of different ecosystems and programming languages. You may find that, even if you have no requirement for any of these particular tools, inspecting their broad implementation details or their specific code may help in generating some ideas of your own. Like the previous iteration, there is no formal criteria for inclusion beyond projects that have caught my eye over time spent online, and the projects have Github repositories. Yes, it's subjective, but there is no qualitative approach to this task that would make any sense.