The inductive biases of trained neural networks are difficult to understand and, consequently, to adapt to new settings.
The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task.
Ranked #11 on Few-Shot Image Classification on CIFAR-FS 5-way (1-shot)
The environment's dynamics are learned from limited training data and can be reused in new task instances without retraining.
A suitable similarity index for comparing learnt neural networks plays an important role in understanding the behaviour of the highly-nonlinear functions, and can provide insights on further theoretical analysis and empirical studies.
2 code implementations • 24 Nov 2019 • Bharathan Balaji, Jordan Bell-Masterson, Enes Bilgin, Andreas Damianou, Pablo Moreno Garcia, Arpit Jain, Runfei Luo, Alvaro Maggiar, Balakrishnan Narayanaswamy, Chun Ye
Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games.
We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10.
Multi-fidelity methods are prominently used when cheaply-obtained, but possibly biased and noisy, observations must be effectively combined with limited or expensive true data in order to construct reliable models.
Approaches that transfer information contained only in the final parameters of a source model will therefore struggle.
This has hindered the application of DGPs in computer vision tasks, an area where deep parametric models (i. e. CNNs) have made breakthroughs.
Experiments show that our framework can accurately learn annotator expertise, infer true labels, and effectively reduce the amount of annotations in model training as compared to state-of-the-art approaches.
We present a new framework for this scenario that we call Preferential Bayesian Optimization (PBO) and that allows to find the optimum of a latent function that can only be queried through pairwise comparisons, so-called duels.
1 code implementation • 12 Jun 2017 • Clément Moulin-Frier, Tobias Fischer, Maxime Petit, Grégoire Pointeau, Jordi-Ysard Puigbo, Ugo Pattacini, Sock Ching Low, Daniel Camilleri, Phuong Nguyen, Matej Hoffmann, Hyung Jin Chang, Martina Zambelli, Anne-Laure Mealier, Andreas Damianou, Giorgio Metta, Tony J. Prescott, Yiannis Demiris, Peter Ford Dominey, Paul F. M. J. Verschure
This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot.
Bayesian optimization (BO) has emerged during the last few years as an effective approach to optimizing black-box functions where direct queries of the objective are expensive.
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities.
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations.
We define Recurrent Gaussian Processes (RGP) models, a general family of Bayesian nonparametric models with recurrent GP priors which are able to learn dynamical patterns from sequential data.
We develop a scalable deep non-parametric generative model by augmenting deep Gaussian processes with a recognition model.
In this work, we present an extension of Gaussian process (GP) models with sophisticated parallelization and GPU acceleration.
In this paper we present a modification to a latent topic model, which makes the model exploit supervision to produce a factorized representation of the observed data.
Our work builds on recent variational approximations for Gaussian process latent variable models to allow for nonlinear dimensionality reduction simultaneously with learning a dynamical prior in the latent space.