# Quest Symposium on Robust, Interpretable
Deep Learning Systems

## Posters

Poster format: up to 48''×72'', paper.

Set up posters at 2:00pm before the event.

Number | Poster Title | Name |
---|---|---|

A01 | On Algorithms for Adversarial Dynamics | Abdullah Al-Dujaili |

A02 | Defense Against Adversarial Attacks using Web-Scale Nearest Neighbors Search | Abhimanyu Dubey |

A03 | Clean-Label Backdoor Attacks | Alexander Turner |

A04 | Generally Exciting Inputs and How to Get Rid Of Them: A Little Network Introspection | Aspen |

A05 | Combining Machine Learning with Deductive Reasoning for Improved Explainability | Ben Z Yuan |

A06 | Safe Reinforcement Learning with Model Uncertainty Estimates for Dynamic Collision Avoidance | Björn Lütjens |

A07 | Evaluating 'Graphical Perception' with CNNs | Daniel Haehn |

A08 | Individual Neurons in Neural Machine Translation | Yonatan Belinkov |

A09 | Robustness may be at odds with accuracy | Dimitris Tsipras |

A10 | Analyzing Gradients to Detect Backdoors in Deep Neural Networks | Ebube Chuba |

A11 | Towards Functional Transparency: a Game-Theoretic Approach | Guang-He Lee |

A12 | All you need to train deep residual networks is a good initialization | Hongyi Zhang |

A13 | ResNet with one-neuron hidden layers is a Universal Approximator | Hongzhou Lin |

A14 | Quantum optical neural networks | Jacques Carolan |

A15 | Comparing deep neural network and human representations via sound synthesis | Jenelle Feather |

A16 | Defensive Quantization: When Efficiency Meets Robustness | Ji Lin |

A17 | The Lottery Ticket Hypothesis | Jonathan Frankle |

A18 | Symbolic Relation Networks for Reinforcement Learning | Josh Joseph |

A19 | Automating Stylistic Bias Detection in Sentiment Analysis | Judy Hanwen Shen |

A20 | Visual Inspection of Saliency Maps Can Provide a False Sense of Security | Julius Adebayo |

B21 | Towards Robust, Locally Linear Deep Networks | Guang-He Lee |

B22 | Learning Symbolic Rules Through Explanation | Leilani H. Gilpin |

B23 | Efficient Neural Network Robustness Certification with General Activation Functions | Lily Weng |

B24 | Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability | Mahi Shafiullah |

B25 | Inverse Graphics with Probabilistic Programming and Deep Learning for Inference | Marco Cusumano-Towner |

B26 | Examining Learned Class Relationships in Deep Neural Networks | Mathew Monfort |

B27 | Neural Networks Trained to Estimate F0 from Natural Sounds Replicate Properties of Human Pitch Perception | Ray Gonzalez |

B28 | Targeted Syntactic Evaluation of LSTMs and Recurrent Neural Network Grammars | Roger Levy |

B29 | Understanding Phase-Coded Neural Networks and their Scalability | Rumen Dangovski |

B30 | Verification of Dynamical Systems with Piecewise Affine Machine Learning Elements | Sadra Sadraddini |

B31 | Minimal Images in Deep Neural Networks: DNN Failures on Natural Images | Sanjana Srivastava |

B32 | Verification of Recurrent Neural Networks via Systems and Control Theory | Shen Shen |

B33 | Utility Interpretation in Deep Neural Network | Shenhao Wang |

B34 | Providing Rationales and Pragmatically Effective Modifications | Sudhanshu Mishra |

B35 | Detecting Egregious Responses in Neurl Sequence-to-Sequence Models | Tianxing He |

B36 | Redundancy Emerges in Overparametrized Deep Neural Networks | Xavier Boix |

B37 | Emergence of topographical correspondences between deep neural network and human brain visual cortex | Yalda Mohsenzadeh |

B38 | Comparing multi-task and single-task network interpretability | Kandan Ramakrishnan |

B39 | Visualizing and Understanding Generative Adversarial Networks | David Bau |