Advances in variational inference
Many modern unsupervised or semi-supervised machine learning algorithms rely on
Bayesian probabilistic models. These models are usually intractable and thus require …
Bayesian probabilistic models. These models are usually intractable and thus require …
Dynamical variational autoencoders: A comprehensive review
L Girin, S Leglaive, X Bie, J Diard, T Hueber… - ar**: Toward the robust-perception age
Simultaneous localization and map** (SLAM) consists in the concurrent construction of a
model of the environment (the map), and the estimation of the state of the robot moving …
model of the environment (the map), and the estimation of the state of the robot moving …
Learning latent dynamics for planning from pixels
Planning has been very successful for control tasks with known environment dynamics. To
leverage planning in unknown environments, the agent needs to learn the dynamics from …
leverage planning in unknown environments, the agent needs to learn the dynamics from …
Deep state space models for time series forecasting
We present a novel approach to probabilistic time series forecasting that combines state
space models with deep learning. By parametrizing a per-time-series linear state space …
space models with deep learning. By parametrizing a per-time-series linear state space …
Model-based reinforcement learning: A survey
Sequential decision making, commonly formalized as Markov Decision Process (MDP)
optimization, is an important challenge in artificial intelligence. Two key approaches to this …
optimization, is an important challenge in artificial intelligence. Two key approaches to this …
KalmanNet: Neural network aided Kalman filtering for partially known dynamics
State estimation of dynamical systems in real-time is a fundamental task in signal
processing. For systems that are well-represented by a fully known linear Gaussian state …
processing. For systems that are well-represented by a fully known linear Gaussian state …
Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model
Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn
directly from image observations. However, these high-dimensional observation spaces …
directly from image observations. However, these high-dimensional observation spaces …