Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on complex tasks. However, if the task at hand deviates excessively from the demonstrated task, the effectiveness of such methods is limited. In our work, we propose to learn features from offline data that are shared by a more diverse range of tasks, such as correlation between actions and directedness. Therefore, we introduce state-free priors, which directly model temporal consistency in demonstrated trajectories, and are capable of driving exploration in complex tasks, even when trained on data collected on simpler tasks. Furthermore, we introduce a novel integration scheme for action priors in off-policy reinforcement learning by dynamically sampling actions from a probabilistic mixture of policy and action prior. We compare our approach against strong baselines and provide empirical evidence that it can accelerate reinforcement learning in long-horizon continuous control tasks under sparse reward settings.

Existing singing voice synthesis models (SVS) are usually trained on singing data and depend on either error-prone time-alignment and duration features or explicit music score information. In this paper, we propose Karaoker, a multispeaker Tacotron-based model conditioned on voice characteristic features that is trained exclusively on spoken data without requiring time-alignments. Karaoker synthesizes singing voice and transfers style following a multi-dimensional template extracted from a source waveform of an unseen singer/speaker. The model is jointly conditioned with a single deep convolutional encoder on continuous data including pitch, intensity, harmonicity, formants, cepstral peak prominence and octaves. We extend the text-to-speech training objective with feature reconstruction, classification and speaker identification tasks that guide the model to an accurate result. In addition to multitasking, we also employ a Wasserstein GAN training scheme as well as new losses on the acoustic model's output to further refine the quality of the model.

We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning. Meta-learning aims to leverage experience gained from previous tasks to solve new tasks efficiently (i.e., with better performance, little training data, and/or modest computational resources). While previous challenges in the series focused on within-domain few-shot learning problems, with the aim of learning efficiently N-way k-shot tasks (i.e., N class classification problems with k training examples), this competition challenges the participants to solve "any-way" and "any-shot" problems drawn from various domains (healthcare, ecology, biology, manufacturing, and others), chosen for their humanitarian and societal impact. To that end, we created Meta-Album, a meta-dataset of 40 image classification datasets from 10 domains, from which we carve out tasks with any number of "ways" (within the range 2-20) and any number of "shots" (within the range 1-20). The competition is with code submission, fully blind-tested on the CodaLab challenge platform. The code of the winners will be open-sourced, enabling the deployment of automated machine learning solutions for few-shot image classification across several domains.

The surge in interest in Artificial Intelligence (AI) over the past decade has been driven almost exclusively by advances in Artificial Neural Networks (ANNs). While ANNs set state-of-the-art performance for many previously intractable problems, the use of global gradient descent necessitates large datasets and computational resources for training, potentially limiting their scalability for real-world domains. Spiking Neural Networks (SNNs) are an alternative to ANNs that use more brain-like artificial neurons and can use local unsupervised learning to rapidly discover sparse recognizable features in the input data. SNNs, however, struggle with dynamical stability and have failed to match the accuracy of ANNs. Here we show how an SNN can overcome many of the shortcomings that have been identified in the literature, including offering a principled solution to the dynamical "vanishing spike problem", to outperform all existing shallow SNNs and equal the performance of an ANN. It accomplishes this while using unsupervised learning with unlabeled data and only 1/50th of the training epochs (labeled data is used only for a simple linear readout layer). This result makes SNNs a viable new method for fast, accurate, efficient, explainable, and re-deployable machine learning with unlabeled data.

Causal machine learning is a field that focuses on using machine learning method to tackle causality problems. Despite the recent progress of this field, there are still many unresolved challenges including missing data, selection bias, unobserved confounders, etc., which are ubiquitous in the real world. Advances in any of the above areas can greatly reduce the gap between research and real world impact. In this competition, we focus on two fundamental challenges of causal machine learning in the context of education using time-series data. The first is to identify the causal relationships between different constructs, where a construct is defined as the smallest element of learning. The second challenge is to predict the impact of learning one construct on the ability to answer questions on other constructs. Addressing these challenges will not only impact the causal ML community but also enable optimisation of students' knowledge acquisition, which can be deployed in a real edtech solution impacting millions of students. Participants will run these tasks in an idealised environment with synthetic data and a real-world scenario with evaluation data collected from a series of A/B tests. We expect participants to develop novel machine learning methodologies for causal discover between different constructs and the impact estimation of learning one construct on other constructs, which should bring fundamental advances to causal ML.

The last decade has shown a growing interest in robots as well-being coaches. However, cohesive and comprehensive guidelines for the design of robots as coaches to promote mental well-being have not yet been proposed. This paper details design and ethical recommendations based on a qualitative meta-analysis drawing on a grounded theory approach, which was conducted with three distinct user-centered design studies involving robotic well-being coaches, namely: (1) a participatory design study conducted with 11 participants consisting of both prospective users who had participated in a Brief Solution-Focused Practice study with a human coach, as well as coaches of different disciplines, (2) semi-structured individual interview data gathered from 20 participants attending a Positive Psychology intervention study with the robotic well-being coach Pepper, and (3) a participatory design study conducted with 3 participants of the Positive Psychology study as well as 2 relevant well-being coaches. After conducting a thematic analysis and a qualitative meta-analysis, we collated the data gathered into convergent and divergent themes, and we distilled from those results a set of design guidelines and ethical considerations. Our findings can inform researchers and roboticists on the key aspects to take into account when designing robotic mental well-being coaches.

This paper introduces Probabilistic Deduction (PD) as an approach to probabilistic structured argumentation. A PD framework is composed of probabilistic rules (p-rules). As rules in classical structured argumentation frameworks, p-rules form deduction systems. In addition, p-rules also represent conditional probabilities that define joint probability distributions. With PD frameworks, one performs probabilistic reasoning by solving Rule-Probabilistic Satisfiability. At the same time, one can obtain an argumentative reading to the probabilistic reasoning with arguments and attacks. In this work, we introduce a probabilistic version of the Closed-World Assumption (P-CWA) and prove that our probabilistic approach coincides with the complete extension in classical argumentation under P-CWA and with maximum entropy reasoning. We present several approaches to compute the joint probability distribution from p-rules for achieving a practical proof theory for PD. PD provides a framework to unify probabilistic reasoning with argumentative reasoning. This is the first work in probabilistic structured argumentation where the joint distribution is not assumed form external sources.

The classification of electroencephalography (EEG) signals is useful in a wide range of applications such as seizure detection/prediction, motor imagery classification, emotion classification and drug effects diagnosis, amongst others. With the large number of EEG channels acquired, it has become vital that efficient data-reduction methods are developed, with varying importance from one application to another. It is also important that online classification is achieved during EEG recording for many applications, to monitor changes as they happen. In this paper we introduce a method based on Mutual Information (MI), for channel selection. Obtained results show that whilst there is a penalty on classification accuracy scores, promising speed-up gains can be achieved using MI techniques. Using MI with signal epochs (3secs) containing signal transitions enhances these speed-up gains. This work is exploratory and we suggest further research to be carried out for validation and development. Benefits to improving classification speed include improving application in clinical or educational settings.

Transformer-based models for transfer learning have the potential to achieve high prediction accuracies on text-based supervised learning tasks with relatively few training data instances. These models are thus likely to benefit social scientists that seek to have as accurate as possible text-based measures but only have limited resources for annotating training data. To enable social scientists to leverage these potential benefits for their research, this paper explains how these methods work, why they might be advantageous, and what their limitations are. Additionally, three Transformer-based models for transfer learning, BERT (Devlin et al. 2019), RoBERTa (Liu et al. 2019), and the Longformer (Beltagy et al. 2020), are compared to conventional machine learning algorithms on three applications. Across all evaluated tasks, textual styles, and training data set sizes, the conventional models are consistently outperformed by transfer learning with Transformers, thereby demonstrating the benefits these models can bring to text-based social science research.

About GANs Generative Adversarial Networks (GANs) are powerful machine learning models capable of generating realistic image, video, and voice outputs. Rooted in game theory, GANs have wide-spread application: from improving cybersecurity by fighting against adversarial attacks and anonymizing data to preserve privacy to generating state-of-the-art images, colorizing black and white images, increasing image resolution, creating avatars, turning 2D images to 3D, and more. About this Specialization The DeepLearning.AI Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach. It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more. Build a comprehensive knowledge base and gain hands-on experience in GANs. Train your own model using PyTorch, use it to create images, and evaluate a variety of advanced GANs.