Sean Welleck's Home Page

The Thesis Review Podcast

Each episode of The Thesis Review is a conversation centered around a researcher's PhD thesis, giving insight into their history, revisiting older ideas, and providing a valuable perspective on how their research has evolved (or stayed the same) since.

Episodes

• [42] Charles Sutton | Efficient Training Methods for Conditional Random Fields
  
  [episode notes]
• [41] Talia Ringer | Proof Repair
  
  [episode notes]
• [40] Lisa Lee | Learning Embodied Agents with Scalably-Supervised Reinforcement Learning
  
  [episode notes]
• [39] Burr Settles | Curious Machines: Active Learning with Structured Instances
  
  [episode notes]
• [38] Andrew Lampinen | A Computational Framework for Learning and Transforming Task Representations
  
  [episode notes]
• [37] Joonkoo Park | Experiential Effects on the Neural Substrates of Visual Word and Number Processing
  
  [episode notes]
• [36] Dieuwke Hupkes | Hierarchy and interpretability in neural models of language processing
  
  [episode notes]
• [35] Armando Solar-Lezama | Program Synthesis by Sketching
  
  [episode notes]
• [34] Sasha Rush | Lagrangian Relaxation for Natural Language Decoding
  
  [episode notes]
• [33] Michael R. Douglas | G/H Conformal Field Theory
  
  [episode notes]
• [32] Andre Martins | The Geometry of Constrained Structured Prediction
  
  [episode notes]
• [31] Jay McClelland | Preliminary Letter Identification in the Perception of Words and Nonwords
  
  [episode notes]
• [30] Dustin Tran | Probabilistic Programming for Deep Learning
  
  [episode notes]
• [29] Tengyu Ma | Non-convex Optimization for Machine Learning: Design, Analysis, and Understanding
  
  [episode notes]
• [28] Karen Ullrich | A Coding Perspective on Deep Latent Variable Models
  
  [episode notes]
• [27] Danqi Chen | Neural Reading Comprehension and Beyond
  
  [episode notes]
• [26] Kevin Ellis | Algorithms for Learning to Induce Programs
  
  [episode notes]
• [25] Tomas Mikolov | Statistical Language Models Based on Neural Networks
  
  [episode notes]
• [24] Martin Arjovsky | Out of Distribution Generalization in Machine Learning
  
  [episode notes]
• [23] Simon Du | Gradient Descent for Non-convex Problems in Modern Machine Learning
  
  [episode notes]
• [22] Graham Neubig | Unsupervised Learning of Lexical Information for Language Processing Systems
  
  [episode notes]
• [21] Michela Paganini | Machine Learning Solutions for High Energy Physics
  
  [episode notes]
• [20] Josef Urban | Exploring and Combining Deductive and Inductive Reasoning in Large Libraries of Formalized Mathematics
  
  [episode notes]
• [19] Dumitru Erhan | Understanding Deep Architectures and the Effect of Unsupervised Pretraining
  
  [episode notes]
• [18] Eero Simoncelli | Distributed Representation & Analysis of Visual Motion
  
  [episode notes]
• [17] Paul Middlebrooks | Neuronal Correlates of Metacognition in Primate Frontal Cortex
  
  [episode notes]
• [16] Aaron Courville | A Latent Cause Theory of Classical Conditioning
  
  [episode notes]
• [15] Christian Szegedy | Some Applications of the Weighted Combinatorial Laplacian
  
  [episode notes]
• [14] Been Kim | Interactive and Interpretable Machine Learning Models for Human Machine Collaboration
  
  [episode notes]
• [13] Adji Bousso Dieng | Deep Probabilistic Graphical Modeling
  
  [episode notes]
• [12] Martha White | Regularized Factor Models
  
  [episode notes]
• [11] Jacob Andreas | Learning from Language
  
  [episode notes]
• [10] Chelsea Finn | Learning to Learn with Gradients
  
  [episode notes]
• [09] Kenneth Stanley | Efficient Evolution of Neural Networks through Complexification
  
  [episode notes]
• [08] He He | Sequential Decisions and Predictions in Natural Language Processing
  
  [episode notes]
• [07] John Schulman | Optimizing Expectations: From Deep RL to Stochastic Computation Graphs
  
  [episode notes]
• [06] Yoon Kim | Deep Latent Variable Models of Natural Language
  
  [episode notes]
• [05] Julian Togelius | Optimization, Imitation, and Innovation: Computational Intelligence and Games
  
  [episode notes]
• [04] Sebastian Nowozin | Learning with Structured Data: Applications to Computer Vision
  
  [episode notes]
• [03] Sebastian Ruder | Neural Transfer Learning for Natural Language Processing
  
  [episode notes]
• [02] Colin Raffel | Learning-Based Methods for Comparing Sequences, with Applications to Audio-to-MIDI Alignment and Matching
  
  [episode notes]
• [01] Gus Xia | Expressive Collaborative Music Performance via Machine Learning
  
  [episode notes]
• [00] Introduction | The Thesis Review Podcast
  [episode notes]