
StateDenoised Recurrent Neural Networks
Recurrent neural networks (RNNs) are difficult to train on sequence proc...
read it

Estimating Forces of Robotic Pouring Using a LSTM RNN
In machine learning, it is very important for a robot to be able to esti...
read it

Visualizing RNN States with Predictive Semantic Encodings
Recurrent Neural Networks are an effective and prevalent tool used to mo...
read it

Internal representation dynamics and geometry in recurrent neural networks
The efficiency of recurrent neural networks (RNNs) in dealing with seque...
read it

LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
Recurrent neural networks, and in particular long shortterm memory (LST...
read it

A Recurrent Neural Network Approach to Roll Estimation for Needle Steering
Steerable needles are a promising technology for delivering targeted the...
read it

Learning to Represent Mechanics via Longterm Extrapolation and Interpolation
While the basic laws of Newtonian mechanics are well understood, explain...
read it
Tustin neural networks: a class of recurrent nets for adaptive MPC of mechanical systems
The use of recurrent neural networks to represent the dynamics of unstable systems is difficult due to the need to properly initialize their internal states, which in most of the cases do not have any physical meaning, consequent to the nonsmoothness of the optimization problem. For this reason, in this paper focus is placed on mechanical systems characterized by a number of degrees of freedom, each one represented by two states, namely position and velocity. For these systems, a new recurrent neural network is proposed: TustinNet. Inspired by secondorder dynamics, the network hidden states can be straightforwardly estimated, as their differential relationships with the measured states are hardcoded in the forward pass. The proposed structure is used to model a double inverted pendulum and for modelbased Reinforcement Learning, where an adaptive Model Predictive Controller scheme using the Unscented Kalman Filter is proposed to deal with parameter changes in the system.
READ FULL TEXT
Comments
There are no comments yet.