Past Events

Tutorial on Deep Learning with Apache MXNet Gluon

  • Where: Bloomberg Building, Room 462
  • When: September 21, 2017 to September 21, 2017, 13:30
  • Alex Smola, PhD, Director of Machine Learning and Deep Learning at AWS

Unfortunately, registration has reached capacity for the “Tutorial on Deep Learning with Apache MXNet Gluon” by Dr. Alex Smola, Director of Machine Learning and Deep Learning at AWS, Carnegie Mellon University, Marianas Labs, CEO. If you really want to attend, and are curious if any seats have become available, you can email one of our … Continued

The Nexus of Data Science, Convergence, and Graduate Education

  • Where: Arellano Theater, Levering Hall
  • When: April 13, 2017, 16:30
  • Dr. Dean Evasius
  • An IDIES Bi-Monthly Seminar

Abstract: Data science has emerged as a distinct discipline that has also become a power enabler of science and engineering. In its deep interactions with other disciplines it is an example of the scientific convergence, which is one of the Ten Big Ideas for Future NSF Investments. The rapid growth of data science raises deep … Continued

What can we learn from human genomics at scale and how do we get there?

  • Where: BSPH E3609 (Genome Café)
  • When: April 03, 2017, 13:30
  • Joe Pickrell
  • A Genomics@JHU Seminar

Abstract: A primary goal of human genetics is to understand the genetic causes of phenotypic variation. Recent successes in genome-wide association studies have shown that achieving this goal requires collecting and analyzing data at scale. I will discuss projects that center around this thesis. First, I will discuss analyses of the genetics of lifespan in … Continued

Decoding epigenetic programs in cellular differentiation and T cell dysfunction in tumors

  • Where: BSPH E2030 (Feinstone)
  • When: May 15, 2017, 13:30
  • Christina Leslie
  • A Genomics@JHU Seminar

Abstract: Dysregulated epigenetic developmental programs are a feature of many cancers, and the diverse differentiation states of immune cells as well as their dysfunctional states in tumors are in part epigenetically encoded. We developed an integrative computational strategy to exploit genome-wide data on chromatin accessibility (DNase-seq or ATAC-seq), histone modifications (ChIP-seq), and transcription (RNA-seq) in … Continued

Data-driven re-annotation of patient tumors and derived model systems

  • Where: BSPH E3609 (Genome Café)
  • When: May 01, 2017, 13:30
  • Benjamin Haibe-Kains
  • A Genomics@JHU Seminar

Abstract: The success of precision medicine largely relies on comprehensive characterization of patient tumors and their derived model systems to select the best therapy for each individual patient. Recent initiatives generated massive amounts of molecular data for healthy (GTEx) and tumor (TCGA) tissues from patients, as well as patient-derived cancer cell lines (Cancer Cell Line … Continued

Mathematical Mysteries of Deep Neural Networks

  • Where: Hodson Hall Board Room
  • When: March 27, 2017 to March 27, 2017, 13:30
  • Stéphane Mallat PhD

Distinguished CIS Seminar Reception directly following seminar. Abstract: Classification and regression require to approximate functions in high dimensional spaces. Avoiding the dimensionality curse opens many questions in statistics, probability, harmonic analysis and geometry. Convolutional deep neural networks can obtain spectacular results for image analysis, speech understanding, natural languages and many other problems. We shall review … Continued

Geometric Methods for the Approximation of High-dimensional Dynamical Systems

  • Where: Mason Hall Auditorium
  • When: February 23, 2017 to February 23, 2017, 16:00
  • Mauro Maggioni
  • An IDIES Bi-Monthly Seminar

Abstract: We discuss a geometry-based statistical learning framework for performing model reduction and modeling of stochastic high-dimensional dynamical systems. We consider two complementary settings. In the first one, we are given long trajectories of a system, e.g. from molecular dynamics, and we discuss new techniques for estimating, in a robust fashion, an effective number of … Continued

Urban Sensing Using Social Media and Cellular Network Data

  • Where: Room 462, Bloomberg Physics and Astronomy Building
  • When: December 09, 2016, 15:00
  • Dr. Dániel Kondor

Please join us on Friday December 9th for a special talk from Dr. Dániel Kondor. Dr. Kondor is a Postdoctoral Research Fellow from the Senseable City Laboratory at MIT. Abstract: Recent developments in communication technologies have brought significant changes to both our everyday lives and data collection technologies and possibilities as well. Nowadays, most of … Continued

Diffusion-based Interactions in Noisy Single Cell Data

  • Where: Charles Commons conference center
  • When: November 14, 2016, 13:30
  • Smita Krishnaswamy
  • A Genomics@JHU Seminar

Abstract Recently, there have been significant advances in single-cell genomic and proteomic technologies that can measure the expression of thousands of mRNA transcripts and dozens of proteins. However, this data suffers from sparsity and noise. Furthermore, its high dimensionality makes interpreting the data difficult for biologists. Our aim is to facilitate interpretation by providing a … Continued

Tumor neoepitope selection for biomarker discovery and therapeutic vaccination

  • Where: Barber Conference Room at Charles Commons, 10 E 33rd St. Baltimore, MD
  • When: October 24, 2016, 13:30
  • Jeff Hammerbacher
  • A Genomics@JHU Seminar

Abstract We’ll review some open source software our lab has developed to facilitate a Phase I clinical trial of a personalized therapeutic vaccine targeting tumor neoepitopes. We’ll also present some results from our analysis of clinical trials of checkpoint blockade in 3 different cancer types and some open source software we’ve created to facilitate similar … Continued