Backprop

2017

Citations in the corpus

• Stochastic Prediction of Multi-Agent Interactions from Partial Observations (2019, methodology): “Our method is also related to the ”backprop Kalman filtering” approach of (Haarnoja et al., 2016).”
• The limits and potentials of deep learning for robotics (2018, background): “…re-composition of component solutions from different places on the spectrum can be achieved with differentiable versions of existing algorithms (one end of the spectrum) that are compatible solutions obtained with back-propagation (other end of the spectrum) [16], [39], [50], [108], [116], [128].”
• Multiple Futures Prediction (2019, unknown): “The bulk of classical methods focus on using physics based dynamic or kinematic models [38, 21, 25].”
• Predictive-State Decoders: Encoding the Future into Recurrent Networks (2017, methodology): “Under a Gaussian assumption (e.g. like a Kalman filter [22]), the equivalent objective that minimizes the negative log-likelihood is given as While traditional methods would explicitly solve for parametric internal states h t using an EM style approach, we use BPTT to implicitly find an…”
• Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs (2015, background): “It is all the more surprising considering that deep neural networks are able to discover non-linear latent variables [9, 3].”
• Chasing Ghosts: Instruction Following as Bayesian State Tracking (2019, background): “However, recent work has demonstrated that Bayes filter implementations – including Kalman filters [28], histogram filters [15] and particle filters [29, 30] – can be embedded into deep neural networks.”
• PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations (2017, methodology): “…and spatial softmax [11], which incorporate priors about visual input as architectural constraints of a neural network, as well as backprop Kalman Filters [3] and end-to-end learnable histogram filters [8], which incorporate the structure of the Bayes’ filter algorithm for recursive state estimation.”