Abstract: Methods and systems are provided to prevent pathological overfitting in training autoencoder networks, by forcing the network to only model structure that is shared between different data variables and to enable an automatic search of hyperparameters in training autoencoder networks, resulting in automated discovery of optimally-trained models. The method may include training a neural network. The training may include applying a first binary mask to the set of training data to determine the training input data. The training may include processing the training input data by the neural network to produce network output data. The training may include determining one or more updates of the parameters based on a comparison of at least a portion of the network output data and a corresponding portion of the training data. The portion of the network output data and the corresponding portion of the training input data being inverts.

Abstract: Systems and methods that use data augmentation during the training of representation learning networks on neuromuscular data (e.g., EMG) with reconstruction cost. The method may include training network(s) on neuromuscular data received from channel(s) of neuromuscular sensor(s). The training may include randomly generating a first augment and a different, second augment for each channel. The training may include augmenting the data of each channel by applying the first and second augments to the data to generate first and second augmented data. The training may include processing at least the first augmented data through at least a first representation learning neural network to determine a first latent representation of one or more neuromuscular activation state variables. The training may include determining a reconstruction cost using the first latent representation and the second augmented data.

Abstract: The disclosures relates to systems and methods for using a trained alignment neural network along with a trained latent representation model to achieve accurate alignment between complex neural signals arising from co-variation across neuron populations over time and their intended motor control that can be invariant for a much longer period without supervised recalibrations. In one implementation, the method may include receiving neural data for a period of time from one or more sensors. The method may further include transforming the neural data to generate aligned variables using a trained alignment network. The method may also include processing the aligned variables through a trained latent model to determine a latent spatiotemporal representation of one or more brain state variables for the period of time and decoding the latent spatiotemporal representation into a brain state for the period of time.

Abstract: Methods and systems are provided to prevent pathological overfitting in training autoencoder networks, by forcing the network to only model structure that is shared between different data variables and to enable an automatic search of hyperparameters in training autoencoder networks, resulting in automated discovery of optimally-trained models. The method may include training a neural network. The training may include applying a first binary mask to the set of training data to determine the training input data. The training may include processing the training input data by the neural network to produce network output data. The training may include determining one or more updates of the parameters based on a comparison of at least a portion of the network output data and a corresponding portion of the training data. The portion of the network output data and the corresponding portion of the training input data being inverts.