Deep Dive into Modern Machine Learning

In this presentation, we will introduce core concepts of modern machine learning, with a focus on different deep learning architectures (such as Convolutional Neural Networks, recurrent networks, and Transformers), as well as aspects of the machine learning life cycle, such as training, application, and evaluation of deep learning models – including approaches to quantify and tackle the challenge of generalization beyond the training data distribution.

Leveraging Behavioral and Neural Data with CEBRA

Mapping behavioral actions to neural activity is a fundamental goal of neuroscience. As our ability to record large neural and behavioral data increases, there is growing interest in modeling neural dynamics during adaptive behaviors to probe neural representations. In particular, neural latent embeddings can reveal underlying correlates of behavior, yet, we lack non-linear techniques that can explicitly and flexibly leverage joint behavior and neural data to uncover neural dynamics.

Supervised Machine Learning for Wearable Sensors

Nowadays, wearable sensors have become ubiquitous in our daily lives, from fitness trackers to smartwatches and health monitoring devices. However, analyzing the data and getting meaningful insights can be challenging. In this workshop, we will investigate the use of supervised machine learning methods, such as Support Vector Machine, Decision Trees, and Artificial Neural Networks, in understanding data from wearable sensors.