Spatiotemporally Resolved Multivariate Pattern Analysis for M/EEG

An emerging goal in neuroscience is tracking what information is represented in brain activity over time as a participant completes some task. Whilst EEG and MEG offer millisecond temporal resolution of how activity patterns emerge and evolve, standard decoding methods present significant barriers to interpretability as they obscure the underlying spatial and temporal activity patterns. We instead propose the use of a generative encoding model framework that simultaneously infers the multivariate spatial patterns of activity and the variable timing at which these patterns emerge on individual trials. An encoding model inversion allows predictions to be made about unseen test data in the same way as in standard decoding methodology. These SpatioTemporally Resolved MVPA (STRM) models can be flexibly applied to a wide variety of experimental paradigms, including classification and regression tasks. We show that these models provide insightful maps of the activity driving predictive accuracy metrics; demonstrate behaviourally meaningful variation in the timing of pattern emergence on individual trials; and achieve predictive accuracies that are either equivalent or surpass those achieved by more widely used methods. This provides a new avenue for investigating the brain's representational dynamics and could ultimately support more flexible experimental designs in future.

Statistical Transfer Learning with Generative Encoding for Spatial Transcriptomics

A new method proposes to align single cell reference datasets to spatial tran- scriptomic genes and tissue images. The technique can transfer single cells to unmeasured histology tissue by first aligning a single cell reference dataset to known Spatial Transcriptomic tissue, and learn from the alignment to predict gene expression on new histology. The model can invert the alignment transformation to generate new histology images from gene expression vectors, allowing for in-silico perturbation analyses through dynamically altering the levels of gene expression. Leveraging the cell atlas can lead to annotation of pathology and clinical specimens, enabling a mapping from the cellular and transcriptomic level to imaging tissue.

Optimization of Generatively Encoded Multi-Material Lattice Structures for Desired Deformation Behavior

Natural systems achieve favorable mechanical properties through coupling significantly different elastic moduli within a single tissue. However, when it comes to man-made materials and structures, there are a lack of methods which enable production of artifacts inspired by these phenomena. In this study, a method for design automation based on alternate deposition of soft and stiff struts within a multi-material 3D lattice structure with desired deformation behavior is proposed. These structures, once external forces are applied, conform to the geometry given in advance. For that purpose, a population-based algorithm was proposed and integrated with a multi-material physics simulator. To reduce the amount of data processed during optimization, a generative encoding method based on discrete cosine transform (DCT) was proposed. This enabled a compressed topological description and promoted symmetry in material distribution. The simulation results showed different three-dimensional lattice structures designed with proposed algorithm to meet a set of desired deformation behaviors. The relation between residual deformation error, targeted deformation geometry, and material distribution is discussed.

Interactions of encoding and decoding problems to understand motor control

Learning a map from movement to neural data (Encoding Problem) and vice versa (Decoding Problem) are crucial to understanding motor control. A principled encoding model that understands underlying neural dynamics can help better solve the decoding problem. Here, we develop a new generative encoding model leveraging deep learning that autonomously captures neural dynamics. After training, the model can synthesize spike trains given any observed kinematics, under the guidance of the learned neural dynamics. When neural data from other sessions or subjects are limited, synthesized spike trains can improve cross-session and cross-subject decoding performance of a Brain Computer Interface decoder. For cross-subject, even with ample data for both subjects, neural dynamics learned from a previous subject can transfer useful knowledge that improves the best achievable decoding performance for the new subject. The approach is general and fully data-driven, and hence could apply to neuroscience encoding and decoding problems beyond motor control.

Learning Fast Quadruped Robot Gaits with the RL PoWER Spline Parameterization

Legged robots are uniquely privileged over their wheeled counterparts in their potential to access rugged terrain. However, designing walking gaits by hand for legged robots is a difficult and time-consuming process, so we seek algorithms for learning such gaits to automatically using real world experimentation. Numerous previous studies have examined a variety of algorithms for learning gaits, using an assortment of different robots. It is often difficult to compare the algorithmic results from one study to the next, because the conditions and robots used vary. With this in mind, we have used an open-source, 3D printed quadruped robot called QuadraTot, so the results may be verified, and hopefully improved upon, by any group so desiring. Because many robots do not have accurate simulators, we test gait-learning algorithms entirely on the physical robot. Previous studies using the QuadraTot have compared parameterized splines, the HyperNEAT generative encoding and genetic algorithm. Among these, the research on the genetic algorithm was conducted by (G l e t t e et al., 2012) in a simulator and tested on a real robot. Here we compare these results to an algorithm called Policy learning by Weighting Exploration with the Returns, or RL PoWER. We report that this algorithm has learned the fastest gait through only physical experiments yet reported in the literature, 16.3% faster than reported for HyperNEAT. In addition, the learned gaits are less taxing on the robot and more repeatable than previous record-breaking gaits.