In this paper, we study the convergence of a class of gradient-based Model-Agnostic Meta-Learning (MAML) methods and characterize their overall computational complexity as well as their best achievable level of accuracy in terms of gradient norm for nonconvex loss functions. In particular, we start with the MAML algorithm and its first order approximation (FO-MAML) and highlight the challenges that emerge in their analysis. By overcoming these challenges not only we provide the first theoretical guarantees for MAML and FO-MAML in nonconvex settings, but also we answer some of the unanswered questions for the implementation of these algorithms including how to choose their learning rate (stepsize) and the batch size for both tasks and datasets corresponding to tasks. In particular, we show that MAML can find an $\epsilon$-first-order stationary point for any positive $\epsilon$ after at most $\mathcal{O}(1/\epsilon^2)$ iterations at the expense of requiring second-order information. We also show that the FO-MAML method which ignores the second-order information required in the update of MAML cannot achieve any small desired level of accuracy, i.e, FO-MAML cannot find an $\epsilon$-first-order stationary point for any positive $\epsilon$. We further propose a new variant of the MAML algorithm called Hessian-free MAML (HF-MAML) which preserves all theoretical guarantees of MAML, without requiring access to the second-order information of loss functions.

In the last few years the systematic adoption of deep learning to visual generation has produced impressive results that, amongst others, definitely benefit from the massive exploration of convolutional architectures. In this paper, we propose a general approach to visual generation that combines learning capabilities with logic descriptions of the target to be generated. The process of generation is regarded as a constrained satisfaction problem, where the constraints describe a set of properties that characterize the target. Interestingly, the constraints can also involve logic variables, while all of them are converted into real-valued functions by means of the t-norm theory. We use deep architectures to model the involved variables, and propose a computational scheme where the learning process carries out a satisfaction of the constraints. We propose some examples in which the theory can naturally be used, including the modeling of GAN and auto-encoders, and report promising results in problems with the generation of handwritten characters and face transformations.

-- Fully autonomous navigation using nano drones has numerous application in the real world, ranging from search and rescue to source seeking. Nano drones are well-suited for source seeking because of their agility, low price, and ubiquitous character . Unfortunately, their constrained form factor limits flight time, sensor payload, and compute capability. These challenges are a crucial limitation for the use of source-seeking nano drones in GPSdenied and highly cluttered environments. Hereby, we introduce a fully autonomous deep reinforcement learning-based light-seeking nano drone. We present the method for efficiently training, converting, and utilizing deep reinforcement learning policies. Our training methodology and novel quantization scheme allow fitting the trained policy in 3 kB of memory. The quantization scheme uses representative input data and input scaling to arrive at a full 8-bit model. Finally, we evaluate the approach in simulation and flight tests using a Bitcraze CrazyFlie, achieving 80% success rate on average in a highly cluttered and randomized test environment. Even more, the drone finds the light source in 29% fewer steps compared to a baseline simulation (obstacle avoidance without source information). T o our knowledge, this is the first deep reinforcement learning method that enables source seeking within a highly constrained nano drone demonstrating robust flight behavior . Our general methodology is suitable for any (source seeking) highly constrained platform using deep reinforcement learning. In recent years, nano drones have gained traction in the robotics community. Their agility, maneuverability, and low price make them suitable for a wide range of applications, especially in GPSdenied and cluttered environments.

To coordinate with other systems, agents must be able to determine what the systems are currently doing and predict what they will be doing in the future---plan and goal recognition. There are many methods for plan and goal recognition, but they assume a passive observer that continually monitors the target system. Real-world domains, where information gathering has a cost (e.g., moving a camera or a robot, or time taken away from another task), will often require a more active observer. We propose to combine goal recognition with other observer tasks in order to obtain \emph{active goal recognition} (AGR). We discuss this problem and provide a model and preliminary experimental results for one form of this composite problem. As expected, the results show that optimal behavior in AGR problems balance information gathering with other actions (e.g., task completion) such as to achieve all tasks jointly and efficiently. We hope that our formulation opens the door for extensive further research on this interesting and realistic problem.

It's Not Whom You Know, It's What You (or Your Friends) Can Do: Succint Coalitional Frameworks for Network Centralities. September 25, 2019 Abstract We investigate the representation of game-theoretic measures of network centrality using a framework that blends a social network representation with the succint formalism of cooperative skill games. We discuss the expressiveness of the new framework and highlight some of its advantages, including a fixed-parameter tractability result for computing centrality measures under such representations. As an application we introduce new network centrality measures that capture the extent to which neighbors of a certain node can help it complete relevant tasks. 1 Introduction Measures of network centrality have a long and rich history in the social sciences [1] and Artificial Intelligence. Such measures have proved useful for a variety of tasks, such as identifying spreading nodes [2] and gatekeepers for information dissemination [3], advertising ...

All natural languages exhibit a distinction between content words (like nouns and adjectives) and function words (like determiners, auxiliaries, prepositions). Yet surprisingly little has been said about the emergence of this universal architectural feature of natural languages. Why have human languages evolved to exhibit this division of labor between content and function words? How could such a distinction have emerged in the first place? This paper takes steps towards answering these questions by showing how the distinction can emerge through reinforcement learning in agents playing a signaling game across contexts which contain multiple objects that possess multiple perceptually salient gradable properties.

Immersive simulations are increasingly used for teaching and training in many societally important arenas including healthcare, disaster response and science education. The interactions of participants in such settings lead to a complex array of emergent outcomes that present challenges for analysis. This paper studies a central element of such an analysis, namely the interpretability of models for inferring structure in time series data. This problem is explored in the context of modeling student interactions in an immersive ecological-system simulation. Unsupervised machine learning is applied to data on system dynamics with the aim of helping teachers determine the effects of students' actions on these dynamics. We address the question of choosing the optimal machine learning model, considering both statistical information criteria and interpretabilty quality. The results of a user study show that the models that are the best understood by people are not those that optimize information theoretic criteria. In addition, a model using a fully Bayesian approach performed well on both statistical measures and on human-subject tests of interpretabilty, making it a good candidate for automated model selection that does not require human-in-the-loop evaluation. The results from this paper are already being used in the classroom and can inform the design of interpretable models for a broad range of socially relevant domains. 1 Introduction There is increasing evidence of the value of multi-person embodied simulations for engaging learners in a variety of applications, such as healthcare, disaster response and education (Alinier et al. 2014; Amir and Gal 2013).

We study the problem of learning properties of nodes in tree structures. Those properties are specified by logical formulas, such as formulas from first-order or monadic second-order logic. We think of the tree as a database encoding a large dataset and therefore aim for learning algorithms which depend at most sublinearly on the size of the tree. We present a learning algorithm for quantifier-free formulas where the running time only depends polynomially on the number of training examples, but not on the size of the background structure. By a previous result on strings we know that for general first-order or monadic second-order (MSO) formulas a sublinear running time cannot be achieved. However, we show that by building an index on the tree in a linear time preprocessing phase, we can achieve a learning algorithm for MSO formulas with a logarithmic learning phase.

--This work aims at developing a system that supports French firefighters in data interpretation during rescue operations. An application ontology is proposed based on existing crisis management ones and operational expertise collection. After that, a knowledge-based system will be developed and integrated in firefighters' environment. Our first studies are shown in this paper. Rescue of people consists in saving their life in case of distress situations by applying responsive operations. In France, it is defined as specific tasks to be accomplished by public services in order to ensure the safety of patients and victims by making them able to escape from dangers, securing intervention sites, providing medical help, and finally, ensuring the evacuation to an appropriate place of reception [1].

Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which only affect a few of the underlying causes. We propose Recurrent Independent Mechanisms (RIMs), a new recurrent architecture in which multiple groups of recurrent cells operate with nearly independent transition dynamics, communicate only sparingly through the bottleneck of attention, and are only updated at time steps where they are most relevant. We show that this leads to specialization amongst the RIMs, which in turn allows for dramatically improved generalization on tasks where some factors of variation differ systematically between training and evaluation.