Few-shot or one-shot learning of classifiers for images or videos is an important next frontier in computer vision. The extreme paucity of training data means that the learning must start with a significant inductive bias towards the type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the target task. However, if the meta-learning phase requires labeled data for a large number of tasks closely related to the target task, it not only increases the difficulty and cost, but also conceptually limits the approach to variations of well-understood domains. In this paper, we propose UMTRA, an algorithm that performs meta-learning on an unlabeled dataset in an unsupervised fashion, without putting any constraint on the classifier network architecture. The only requirements towards the dataset are: sufficient size, diversity and number of classes, and relevance of the domain to the one in the target task. Exploiting this information, UMTRA generates synthetic training tasks for the meta-learning phase. We evaluate UMTRA on few-shot and one-shot learning on both image and video domains. To the best of our knowledge, we are the first to evaluate meta-learning approaches on UCF-101. On the Omniglot and Mini-Imagenet few-shot learning benchmarks, UMTRA outperforms every tested approach based on unsupervised learning of representations, while alternating for the best performance with the recent CACTUs algorithm. Compared to supervised model-agnostic meta-learning approaches, UMTRA trades off some classification accuracy for a vast decrease in the number of labeled data needed. For instance, on the five-way one-shot classification on the Omniglot, we retain 85% of the accuracy of MAML, a recently proposed supervised meta-learning algorithm, while reducing the number of required labels from 24005 to 5.

Machine-learning based dialogue managers are able to learn complex behaviors in order to complete a task, but it is not straightforward to extend their capabilities to new domains. We investigate different policies' ability to handle uncooperative user behavior, and how well expertise in completing one task (such as restaurant reservations) can be reapplied when learning a new one (e.g. booking a hotel). We introduce the Recurrent Embedding Dialogue Policy (REDP), which embeds system actions and dialogue states in the same vector space. REDP contains a memory component and attention mechanism based on a modified Neural Turing Machine, and significantly outperforms a baseline LSTM classifier on this task. We also show that both our architecture and baseline solve the bAbI dialogue task, achieving 100% test accuracy.

The forensic investigation of a terrorist attack poses a huge challenge to the investigative authorities, as several thousand hours of video footage need to be spotted. To assist law enforcement agencies (LEA) in identifying suspects and securing evidences, we present a platform which fuses information of surveillance cameras and video uploads from eyewitnesses. The platform integrates analytical modules for different input-modalities on a scalable architecture. Videos are analyzed according their acoustic and visual content. Specifically, Audio Event Detection is applied to index the content according to attack-specific acoustic concepts. Audio similarity search is utilized to identify similar video sequences recorded from different perspectives. Visual object detection and tracking are used to index the content according to relevant concepts. The heterogeneous results of the analytical modules are fused into a distributed index of visual and acoustic concepts to facilitate rapid start of investigations, following traits and investigating witness reports.

We introduce two novel tree search algorithms that use a policy to guide search. The first algorithm is a best-first enumeration that uses a cost function that allows us to prove an upper bound on the number of nodes to be expanded before reaching a goal state. We show that this best-first algorithm is particularly well suited for "needle-in-a-haystack" problems. The second algorithm is based on sampling and we prove an upper bound on the expected number of nodes it expands before reaching a set of goal states. We show that this algorithm is better suited for problems where many paths lead to a goal. We validate these tree search algorithms on 1,000 computer-generated levels of Sokoban, where the policy used to guide the search comes from a neural network trained using A3C. Our results show that the policy tree search algorithms we introduce are competitive with a state-of-the-art domain-independent planner that uses heuristic search.

AI is as hot as a laptop with a broken fan--so scorching that some conferences promise to exclude recruiters. As such, there are plenty of organizations motivated to share AI and machine learning information. This overview aims to help you identify the conferences that are worth your time and meet your needs. At first glance, you could use a background in data mining just to sort through all the events that have "artificial Intelligence" in their titles or include AI conference tracks. I winnowed down the offerings based on the quality of speakers, attendees, and networking opportunities.

This course, taught originally at UCL and recorded for online access, has two interleaved parts that converge towards the end of the course. One part is on machine learning with deep neural networks, the other part is about prediction and control using reinforcement learning. The two strands come together when we discuss deep reinforcement learning, where deep neural networks are trained as function approximators in a reinforcement learning setting. The deep learning stream of the course will cover a short introduction to neural networks and supervised learning with TensorFlow, followed by lectures on convolutional neural networks, recurrent neural networks, end-to-end and energy-based learning, optimization methods, unsupervised learning as well as attention and memory. Possible applications areas to be discussed include object recognition and natural language processing.

Summary: This may be the golden age of deep learning but a lot can be learned by looking at where deep neural nets aren't working yet. This can be a guide to calming the hype. It can also be a roadmap to future opportunities once these barriers are behind us. We are living in the golden age of deep learning. This is quite literally the technology that launched 10,000 startups (to paraphrase Kevin Kelly's prophetic prediction from 2014 "The business plans of the next 10,000 startups are easy to forecast: Take X and add AI.") Well that happened.

The oncoming dawn of an AI dominated age has sparked an enormous amount of literature on the subject over the past few years. A number of fascinating books have come out in 2018 that deal with both the micro and the macro-level effects of Artificial Intelligence on society, politics and the economy. "How deep learning – from Google Translate to driverless cars to personal cognitive assistants – is changing our lives and transforming every sector of the economy. The deep learning revolution has brought us driverless cars, the greatly improved Google Translate, fluent conversations with Siri and Alexa, and enormous profits from automated trading on the New York Stock Exchange. Deep learning networks can play poker better than professional poker players and defeat a world champion at Go. In this book, Terry Sejnowski explains how deep learning went from being an arcane academic field to a disruptive technology in the information economy."

Researchers have shown that rapidly improving AI techniques can facilitate the creation of fake images that look real. As these kinds of technologies move into the language field as well, Howard says, we may need to be more skeptical than ever about what we encounter online. These new language systems learn by analysing millions of sentences written by humans. A system built by OpenAI, a lab based in San Francisco, analysed thousands of self-published books, including romance novels, science fiction and more. Each system learned a particular skill by analysing all that text.

Algorithms are increasingly common components of high-impact decision-making, and a growing body of literature on adversarial examples in laboratory settings indicates that standard machine learning models are not robust. This suggests that real-world systems are also susceptible to manipulation or misclassification, which especially poses a challenge to machine learning models used in financial services. We use the loan grade classification problem to explore how machine learning models are sensitive to small changes in user-reported data, using adversarial attacks documented in the literature and an original, domain-specific attack. Our work shows that a robust optimization algorithm can build models for financial services that are resistant to misclassification on perturbations. To the best of our knowledge, this is the first study of adversarial attacks and defenses for deep learning in financial services.