Boston Machine Learning

Table of Contents

• Intro to Data Science
• Web Scraping
• Theano
• Data Visualization
• Semi-supervised Learning
• Dealing with Temporal Clinical Data
• RNNs and Hyperparameters
• Bayesian Methods
• Distributed Learning
• Techniques for Dimensionality Reduction
• Modeling Sensor Data
• Introduction to Markov Decision Processes
• Perception as Analysis by Synthesis
• Operationalizing Data Science Output
• GPU Accelerated Learning
• High Dimensional Function Learning

Intro to Data Science

• Imran Malek is a Solutions Architect at DataXu. His workshop introduced pandas and matplotlib. Slides | Notebook

Web Scraping

• Marcus Way is an SDE at Amazon and was previously a Software Engineer at Wanderu, a company that helps people find the lowest bus fares. This workshop took us through the process of acquiring data from the web before building a model to predict whether an article's title originated from Gawker or the Wall Street Journal. Notebook

Theano

• Alec Radford is the Head of Research at indico. His talk introduced Theano and convolutional networks. Video | Code

Data Visualization

• Lane Harrison is an Assistant Professor of Computer Science at WPI and was previously a Postdoc in the Visual Analytics Lab at Tufts. His workshop introduced data visualization with d3.js. Slides | Code

Semi-supervised Learning

• Eli Brown is an Assistant Professor of Computer Science at DePaul. His talk focused on using interactive visualizations to help users leverage learning algorithms. Slides | Paper

Dealing with Temporal Clinical Data

• Marzyeh Ghassemi is a PhD Student at MIT CSAIL in the Clinical Decision Making Group. Her session introduced both Latent Dirchlet Allocation and Gaussian Processes before walking us through her recent paper entitled "A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous Clinical Data." Paper | Slides

RNNs and Hyperparameters

• Alec Radford - Using Passage to Train RNNs. Slides | Code | Video

• David Duvenaud - Gradient-Based Learning of Hyperparameters. Paper | Slides | Code

Bayesian Methods

• Allen Downey is a Professor of Computer Science at Olin College. His talk focused on an application of bayesian statistics from World War II. Slides | Video

• José Miguel Hernández Lobato is a Postdoc at Harvard's Intelligent Probabilistic Systems Lab and presented on bayesian optimization and information-based approaches. Slides

Distributed Learning

• Arno Candel is the Chief Architect at H2o. His talk focused on the implementation and application of distributed machine learning algorithms such as Elastic Net, Random Forest, Gradient Boosting, and Deep Neural Networks. Slides

Techniques for Dimensionality Reduction

• Dan Steinburg is a PhD student in intelligent systems at the University of Pittsburgh. His talked introduced various techniques for dimensionality reduction including PCA, multidimensional scaling, isomaps, locally linear embedding, and laplacian eigenmaps. Slides

Modeling Sensor Data

• Hank Roark is a Data Scientist at H2O, where he works on building data products within the domains of machine prognostics, health management, and agriculture. His workshop focused on on the challenges faced when modeling streaming sensor data. Slides | Notebook

Introduction to Markov Decision Processes

• Alborz Geramifard is a Research Scientist at Amazon and lead an introductory workshop on MDPs with RLPy. Paper | Code | Slides

Perception as Analysis by Synthesis

• Tejas Kulkarni is a PhD Student at MIT in Josh Tenenbaum's lab and spent last summer working at Google DeepMind in London. His talk will was focused on his recent paper entitled: "Picture: A Probabilistic Programming Language for Scene Perception." Paper | Slides

Operationalizing Data Science Output

• Tom LaGatta is a Senior Data Scientist & Analytics Architect at Splunk. His session focused on aligning data science output with operational workflows. Slides

GPU Accelerated Learning

• Bob Crovella joined NVIDIA in 1998 and leads a technical team that is responsible for supporting GPU Computing Products. His talk began with an introduction to why GPUs are helpful when training deep neural networks. He then walked through demos of cuDNN and DIGITS from the perspective of how they fit together with frameworks like Caffe, Torch, and Theano. Slides

High Dimensional Function Learning

Jason Klusowski is a PhD student at Yale and presented on the computational and theoretical aspects of approximating d-dimensional functions. Slides