As demand for K-12 computer science (CS) education grows, we argue that most students would be best served by CS classes that not only teach computational thinking/programming, but also challenge them to critically analyze the role of technology in society. One of the main barriers to implementing this in K-12 classrooms is a lack of research on how in-service CS teachers can integrate critical pedagogy into their school context and existing curricula. This poster presents results from a study to co-design lessons with current K-12 CS teachers to integrate critical perspectives into their classrooms. Teacher participants participated in a synchronous professional learning series in which we taught them critical computing content drawn from relevant books and frameworks. Following this, we collaborated with the teacher participants to design or modify lessons that engage their students in critical analysis, which the participants then implemented in their classrooms. Teachers were encouraged to include content relevant to their students and the communities they are a part of. We conducted thematic analysis of transcripts from the interviews, professional learning series, and co-design sessions. The resulting eight (8) themes demonstrate the challenges and opportunities inherent in integrating critical perspectives into K-12 computing education. In the long term, results from this work will inform future sociocultural content integration into K-12 CS courses (e.g. ''ethics content'').

Latent stochastic differential equation (SDE) models are important tools for the unsupervised discovery of dynamical systems from data, with applications ranging from engineering to neuroscience. In these complex domains, exact posterior inference of the latent state path is typically intractable, motivating the use of approximate methods such as variational inference (VI). However, existing VI methods for inference in latent SDEs often suffer from slow convergence and numerical instability. Here, we propose SDE Inference via Natural Gradients (SING), a method that leverages natural gradient VI to efficiently exploit the underlying geometry of the model and variational posterior. SING enables fast and reliable inference in latent SDE models by approximating intractable integrals and parallelizing computations in time. We provide theoretical guarantees that SING will approximately optimize the intractable, continuous-time objective of interest. Moreover, we demonstrate that better state inference enables more accurate estimation of nonlinear drift functions using, for example, Gaussian process SDE models. SING outperforms prior methods in state inference and drift estimation on a variety of datasets, including a challenging application to modeling neural dynamics in freely behaving animals. Altogether, our results illustrate the potential of SING as a tool for accurate inference in complex dynamical systems, especially those characterized by limited prior knowledge and non-conjugate structure.

Understanding how the collective activity of neural populations relates to computation and ultimately behavior is a key goal in neuroscience. To this end, statistical methods which describe high-dimensional neural time series in terms of low-dimensional latent dynamics have played a fundamental role in characterizing neural systems. Yet, what constitutes a successful method involves two opposing criteria: (1) methods should be expressive enough to capture complex nonlinear dynamics, and (2) they should maintain a notion of interpretability often only warranted by simpler linear models. In this paper, we develop an approach that balances these two objectives: the Gaussian Process Switching Linear Dynamical System (gpSLDS). Our method builds on previous work modeling the latent state evolution via a stochastic differential equation whose nonlinear dynamics are described by a Gaussian process (GP-SDEs). We propose a novel kernel function which enforces smoothly interpolated locally linear dynamics, and therefore expresses flexible -- yet interpretable -- dynamics akin to those of recurrent switching linear dynamical systems (rSLDS). Our approach resolves key limitations of the rSLDS such as artifactual oscillations in dynamics near discrete state boundaries, while also providing posterior uncertainty estimates of the dynamics. To fit our models, we leverage a modified learning objective which improves the estimation accuracy of kernel hyperparameters compared to previous GP-SDE fitting approaches. We apply our method to synthetic data and data recorded in two neuroscience experiments and demonstrate favorable performance in comparison to the rSLDS.

In advertising, identifying the content safety of web pages is a significant concern since advertisers do not want brands to be associated with threatening content. At the same time, publishers would like to maximize the number of web pages on which they can place ads. Thus, a fine balance must be achieved while classifying content safety in order to satisfy both advertisers and publishers. In this paper, we propose a multimodal machine learning framework that fuses visual and textual information from web pages to improve current predictions of content safety. The primary focus is on late fusion, which involves combining final model outputs of separate modalities, such as images and text, to arrive at a single decision. This paper presents a fully automated machine learning framework that performs binary and multilabel classification using late fusion techniques. We also introduce additional work in early fusion, which involves extracting and fusing intermediate features from the two separate models. Our algorithms are applied to data extracted from relevant web pages in the advertising industry. Both of our late and early fusion methods obtain significant improvements over algorithms currently in use.

Through high-throughput RNA sequencing (RNAseq), transcriptomes for a single cell, tissue, or organism(s) can be ascertained at a high resolution. While a number of bioinformatic tools have been developed for transcriptome analyses, significant challenges exist for studies of non-model organisms. Without a reference sequence available, raw reads must first be assembled de novo followed by the tedious task of BLAST searches and data mining for functional information. We have created a pipeline, PyRanger, to automate this process. The pipeline includes functionality to assess a single transcriptome and also facilitate comparative transcriptomic studies.