In many applications of modern supervised learning, such as medical imaging or robotics, a large number of tasks is available but many of them are associated with a small amount of data. With few datapoints per task, learning them in isolation would give poor results. In this paper, we consider the problem of learning from a (large) sequence of regression or classification tasks with small sample size. By exploiting their similarities we seek to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Inspired by human ingenuity in solving new problems by leveraging prior experience, meta-learning is a subfield of machine learning whose goal is to automatically adapt a learning mechanism from past experiences to rapidly learn new tasks with little available data. Since it "learns the learning mechanism" it is also referred to as learning-to-learn [34].

Despite interest in communicating ethical problems and social contexts within the undergraduate curriculum to advance Public Interest Technology (PIT) goals, interventions at the graduate level remain largely unexplored. This may be due to the conflicting ways through which distinct Artificial Intelligence (AI) research tracks conceive of their interface with social contexts. In this paper we track the historical emergence of sociotechnical inquiry in three distinct subfields of AI research: AI Safety, Fair Machine Learning (Fair ML) and Human-in-the-Loop (HIL) Autonomy. We show that for each subfield, perceptions of PIT stem from the particular dangers faced by past integration of technical systems within a normative social order. We further interrogate how these histories dictate the response of each subfield to conceptual traps, as defined in the Science and Technology Studies literature. Finally, through a comparative analysis of these currently siloed fields, we present a roadmap for a unified approach to sociotechnical graduate pedagogy in AI.

Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for referring expression comprehension, and a language decoder for image captioning, etc. To alleviate these hassles, in this work, we propose a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation, where our models learn to generate labels in text based on the visual and textual inputs. On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our generative approach (with a single unified architecture) reaches comparable performance to recent task-specific state-of-the-art vision-and-language models. Moreover, our generative approach shows better generalization ability on answering questions that have rare answers. In addition, we show that our framework allows multi-task learning in a single architecture with a single set of parameters, which achieves similar performance to separately optimized single-task models. Our code will be publicly available at: https://github.com/j-min/VL-T5

Neural networks (NNs) are known for their high predictive accuracy in complex learning problems. Beside practical advantages, NNs also indicate favourable theoretical properties such as universal approximation (UA) theorems. Binarized Neural Networks (BNNs) significantly reduce time and memory demands by restricting the weight and activation domains to two values. Despite the practical advantages, theoretical guarantees based on UA theorems of BNNs are rather sparse in the literature. We close this gap by providing UA theorems for fully connected BNNs under the following scenarios: (1) for binarized inputs, UA can be constructively achieved under one hidden layer; (2) for inputs with real numbers, UA can not be achieved under one hidden layer but can be constructively achieved under two hidden layers for Lipschitz-continuous functions. Our results indicate that fully connected BNNs can approximate functions universally, under certain conditions.

Interactive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time. Current interactive reinforcement learning research has been limited to interactions that offer relevant advice to the current state only. Additionally, the information provided by each interaction is not retained and instead discarded by the agent after a single-use. In this work, we propose a persistent rule-based interactive reinforcement learning approach, i.e., a method for retaining and reusing provided knowledge, allowing trainers to give general advice relevant to more than just the current state. Our experimental results show persistent advice substantially improves the performance of the agent while reducing the number of interactions required for the trainer. Moreover, rule-based advice shows similar performance impact as state-based advice, but with a substantially reduced interaction count.

Microsoft is opening up limited access to a text-to-speech AI called Custom Neural Voice, which allows developers to create custom synthetic voices. The tech is part of an Azure AI service called Speech. Companies can use the tech for things like voice-powered smart assistants and devices, chatbots, online learning and reading audiobooks or news. They'll have to apply for access and gain approval from Microsoft before they can harness Custom Neural Voice. The tech can deliver more natural-sounding voices than many other text-to-speech services, according to Microsoft.

Looking for Artificial Intelligence Tutorial to learn introduction to artificial intelligence? Grab the list of Best Artificial Intelligence Courses Online, Tutorials, and Training are offered by a number of massive open online course (MOOC) providers like Udemy, Coursera, and edX. Artificial Intelligence (AI) and machine intelligence are the most booming topics in every industry now. Some of these popular MOOC providers offer some in-depth artificial intelligence programs. The list of the Best Artificial Intelligence Certification is often taught by industry top AI researchers or experts and you will learn the best applications of artificial intelligence.

The optimization of reactions used to synthesize target compounds is pivotal to chemical research and discovery, whether in developing a route for manufacturing a life-saving medicine1 or unlocking the potential of a new material2. But reaction optimization requires iterative experiments to balance the often conflicting effects of numerous coupled variables, and frequently involves finding the sweet spot among thousands of possible sets of experimental conditions. Expert synthetic chemists currently navigate this expansive experimental void using simplified model reactions, heuristic approaches and intuition derived from observation of experimental data3. Writing in Nature, Shields et al.4 report machine-learning software that can optimize diverse classes of reaction with fewer iterations, on average, than are needed by humans. Machine learning has emerged as a useful tool for various aspects of chemical synthesis, because it is ideally suited to extrapolating predictive models that are used to solve synthetic problems by recognizing patterns in multidimensional data sets5.

This paper presents a novel version of the hypergraph neural network method. This method is utilized to solve the noisy label learning problem. First, we apply the PCA dimensional reduction technique to the feature matrices of the image datasets in order to reduce the "noise" and the redundant features in the feature matrices of the image datasets and to reduce the runtime constructing the hypergraph of the hypergraph neural network method. Then, the classic graph-based semi-supervised learning method, the classic hypergraph based semi-supervised learning method, the graph neural network, the hypergraph neural network, and our proposed hypergraph neural network are employed to solve the noisy label learning problem. The accuracies of these five methods are evaluated and compared. Experimental results show that the hypergraph neural network methods achieve the best performance when the noise level increases. Moreover, the hypergraph neural network methods are at least as good as the graph neural network.

Deep learning (DL) has gained much attention and become increasingly popular in modern data science. Computer scientists led the way in developing deep learning techniques, so the ideas and perspectives can seem alien to statisticians. Nonetheless, it is important that statisticians become involved -- many of our students need this expertise for their careers. In this paper, developed as part of a program on DL held at the Statistical and Applied Mathematical Sciences Institute, we address this culture gap and provide tips on how to teach deep learning to statistics graduate students. After some background, we list ways in which DL and statistical perspectives differ, provide a recommended syllabus that evolved from teaching two iterations of a DL graduate course, offer examples of suggested homework assignments, give an annotated list of teaching resources, and discuss DL in the context of two research areas.