Topic: generative models

EMBO | EMBL Symposium bringing machine-learning and life-science researchers together across sequencing, imaging and structural biology. Topics include foundation models, cross-modality learning, causal explanation, mechanistic interpretability, generative models and AI agents. Onsite workshops and tutorials take place on the first day; the following three days offer hybrid talks and posters. Registration is not yet open; the official page accepts expressions of interest.

Gaze shifts in humans serve to direct high-resolution vision provided by the fovea towards areas in the environment. Gaze can be considered a proxy for attention or indicator of the relative importance of different parts of the environment. In this talk, we discuss the development of generative models of human gaze in response to visual input. We discuss how such models can be learned, both using supervised learning and using implicit feedback as an agent interacts with the environment, the latter being more plausible in biological agents. We also discuss two ways such models can be used. Firs

Developing agents capable of modeling complex environments and human behaviors within them is a key goal of artificial intelligence research. Progress towards this goal has exciting potential for applications in video games, from new tools that empower game developers to realize new creative visions, to enabling new kinds of immersive player experiences. This talk focuses on recent advances of my team at Microsoft Research towards scalable machine learning architectures that effectively capture human gameplay data. In the first part of my talk, I will focus on diffusion models as generative mo

Developing agents capable of modeling complex environments and human behaviors within them is a key goal of artificial intelligence research. Progress towards this goal has exciting potential for applications in video games, from new tools that empower game developers to realize new creative visions, to enabling new kinds of immersive player experiences. This talk focuses on recent advances of my team at Microsoft Research towards scalable machine learning architectures that effectively capture human gameplay data. In the first part of my talk, I will focus on diffusion models as generative mo

Elucidating the neural basis of cognition requires incorporating cognitive models into the modelling of neural data. A prevalent strategy in neuroimaging is to fit computational models of cognition to concurrent behavior, and then regress the latent variables of those models onto fMRI data. Though widely used, this approach is restricted to mapping computational variables that are in some way expressed in behavior. Here we introduce a computational parametric mapping (CPM), a framework which builds on and generalizes the Bayesian population receptive field framework. CPM offers three main adva

3D Morphable Models are my favorite class of generative models and are commonly used to model faces. They are typically applied to ill-posed problems such as 3D reconstruction from 2D data. I'll start my presentation with an introduction into 3D Morphable Models and show what they are capable of doing. I'll then focus on our recent finding, the Identity-Expression Ambiguity: We demonstrate that non-orthogonality of the variation in identity and expression can cause identity-expression ambiguity in 3D Morphable Models, and that in practice expression and identity are far from orthogonal and can

This talk will focus on the generative modelling of resting state time series or endogenous neuronal activity. I will survey developments in modelling distributed neuronal fluctuations – spectral dynamic causal modelling (DCM) for functional MRI – and how this modelling rests upon functional connectivity. The dynamics of brain connectivity has recently attracted a lot of attention among brain mappers. I will also show a novel method to identify dynamic effective connectivity using spectral DCM. Further, I will summarise the development of the next generation of DCMs towards large-scale, whole-

The human brain is a complex network of neuronal connections. The precise arrangement of these connections, otherwise known as the topology of the network, is crucial to its functioning. Recent efforts to understand how the complex topology of the brain has emerged have used generative mathematical models, which grow synthetic networks according to specific wiring rules. Evidence suggests that a wiring rule which emulates a trade-off between connection costs and functional benefits can produce networks that capture essential topological properties of brain networks. In this webinar, Professor

Despite the large number of active neurons in the cortex, the activity of neuronal populations is expected to lie on a low-dimensional manifold for different brain regions [1]. Variants of principal component analysis (PCA) are commonly used to assess this manifold. However, these methods are limited by the assumption that the data follows a Gaussian distribution and neglect additional features such as the curvature of the manifold. Hence, their performance as generative models tends to be subpar. To construct a generative model that entirely learns the statistics of neural activity with no a

Understanding how visual attributes influence cognitive properties, such as memorability and emotional valence, is crucial for advancements in computational neuroscience and AI-driven image processing. Previous work has introduced a research framework that uses generative models to learn the complex nonlinear mapping between visual attributes and cognitive properties (Goetschalckx et al., 2019). This approach identifies transformations in the latent space of a generative model, which, when applied, generate images with tailored visual attributes that can enhance or diminish targeted cognitive