University of Cambridge > > women@CL Speaker Lunch Series > Women @Cl Talklet Event

Women @Cl Talklet Event

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Ayat Fekry.


Speaker: Mariana Marasoiu

Title: Towards end-user tools for interactive data visualisation

Abstract: More data is being generated today than ever before, and the number of people wanting to analyse and understand this data is growing. Much of this data analysis is done using visualisations, from simple bar charts and scatter plots to interactive dashboards and infographics. Unfortunately, the existing tools for visual data exploration are not very accessible to non-experts. In order to ground the design of new tools for non-expert end-users in the real-world practice of data analysts, I have conducted an ethnographically informed study of a team of expert visual analysts. In this talk, I will summarise this fieldwork and will discuss early designs for a new visualisation tool.


Speaker: Maria Perez-Ortiz

Title: Learning from humans and the law of comparative judgment

Abstract:The problem of how to elicit judgments from humans has its roots in the well-established fields of psychophysics and sensory evaluation and is of crucial interest in applications involving subjective judgments. Methods for elicitation of human judgments are usually categorised under the term of scaling, i.e. the generation of a scale of the observer’s response to a stimuli. Scaling methods attempt to represent preference judgments on a line or multidimensional space, so as to effectively retain distances between tested objects. This scale usually reveals the underlying structure or unique relationships among the objects, allowing to measure and compare them in a meaningful way. This talk will review some of these approaches.


Speaker: Helena Andrés Terre

Title: Using Auto-Encoders to interpret Single Cell Transcriptomic Data

Abstract: The introduction of single cell RNA -seq was a major breakthrough in the eld of biology, and particularly useful for research in areas like comparative transcriptomics or disease studies. Stem Cell’s di erentiation has also bene ted from this new technique, being able now to characterise gene expression levels for individual cells, and analyse the different stages of the differentiation process. Computational analysis of such data is essential to understand the experimental results, therefore new techniques are needed in order to process and interpret the data. Our goal is to identify the most relevant drivers of the underlying processes captured by the gene expression pro les. Current methods are based on linear dimensionality reduction techniques, combined with further analysis to classify the cells and identify the di erentiation stages. But the nature of their assumptions generate some restrictions when trying to characterise middle states of differentiation. We have developed an unsupervised Machine Learning technique for dimensionality reduction of single cell data. We are using Auto-Encoders to extract a number of signi cant components that characterise individual cells based on their gene expression, using a deep learning “bottle-neck” approach. The encoded space provides a new representation of the individual cells with uncorrelated components, which can then be used for further analysis and classi cation. The reconstruction ability of Autoencoders can also give an insight on the noise level and relevance of speci c genes to the process. We evaluate the performance of these networks in terms of reconstruction accuracy and the information transferred to the encoded dimensions. I will give an overview of the implementation and the rst results we have obtained, together with some of the future challenges and questions we will be tackling.

This talk is part of the women@CL Speaker Lunch Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2018, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity