Multiplicative Latent Force Model google
Bayesian modelling of dynamic systems must achieve a compromise between providing a complete mechanistic specification of the process while retaining the flexibility to handle those situations in which data is sparse relative to model complexity, or a full specification is hard to motivate. Latent force models achieve this dual aim by specifying a parsimonious linear evolution equation which an additive latent Gaussian process (GP) forcing term. In this work we extend the latent force framework to allow for multiplicative interactions between the GP and the latent states leading to more control over the geometry of the trajectories. Unfortunately inference is no longer straightforward and so we introduce an approximation based on the method of successive approximations and examine its performance using a simulation study. …

Articulate google
Articulate is a platform for building conversational interfaces with intelligent agents. Articulate is an open source project that will allow you to take control of you conversational interfaces, without being worried where and how your data is stored. Also, Articulate is built with an user-centered design where the main goal is to make experts and beginners feel comfortable when building their intelligent agents.
The main features of Articulate are:
• Open source project
• Based on Rasa NLU
• Docker and docker-compose based (Easy to set up locally and in the cloud)
• Awesome UI/UX
• Webhook connection
• Response formatting
• Handlebars.js for template responses
• Community support on Gitter and Github
Articulates makes it super easy to get up and running with Rasa NLU. You´ll be guided as you build and train your custom agent using our friendly and intuitive interface. …

Structured Control Net (SCN) google
In recent years, Deep Reinforcement Learning has made impressive advances in solving several important benchmark problems for sequential decision making. Many control applications use a generic multilayer perceptron (MLP) for non-vision parts of the policy network. In this work, we propose a new neural network architecture for the policy network representation that is simple yet effective. The proposed Structured Control Net (SCN) splits the generic MLP into two separate sub-modules: a nonlinear control module and a linear control module. Intuitively, the nonlinear control is for forward-looking and global control, while the linear control stabilizes the local dynamics around the residual of global control. We hypothesize that this will bring together the benefits of both linear and nonlinear policies: improve training sample efficiency, final episodic reward, and generalization of learned policy, while requiring a smaller network and being generally applicable to different training methods. We validated our hypothesis with competitive results on simulations from OpenAI MuJoCo, Roboschool, Atari, and a custom 2D urban driving environment, with various ablation and generalization tests, trained with multiple black-box and policy gradient training methods. The proposed architecture has the potential to improve upon broader control tasks by incorporating problem specific priors into the architecture. As a case study, we demonstrate much improved performance for locomotion tasks by emulating the biological central pattern generators (CPGs) as the nonlinear part of the architecture. …

Distributionally Robust Stochastic Optimization (DRSO) google
A central question in statistical learning is to design algorithms that not only perform well on training data, but also generalize to new and unseen data. In this paper, we tackle this question by formulating a distributionally robust stochastic optimization (DRSO) problem, which seeks a solution that minimizes the worst-case expected loss over a family of distributions that are close to the empirical distribution in Wasserstein distances. We establish a connection between such Wasserstein DRSO and regularization. More precisely, we identify a broad class of loss functions, for which the Wasserstein DRSO is asymptotically equivalent to a regularization problem with a gradient-norm penalty. Such relation provides new interpretations for problems involving regularization, including a great number of statistical learning problems and discrete choice models (e.g. multinomial logit). The connection suggests a principled way to regularize high-dimensional, non-convex problems. This is demonstrated through two applications: the training of Wasserstein generative adversarial networks (WGANs) in deep learning, and learning heterogeneous consumer preferences with mixed logit choice model. …