This is the wiki for the Sabuncu Lab's journal club (or paper reading group). You can find information on the meeting format, schedule, papers and presenters.
SCHEDULE (Fall 2023)
Thursdays 2-3pm @ Zoom
AREAS OF INTEREST
Machine learning, computer vision, image processing, statistical modeling and inference, biomedical image/data analysis, …
FORMAT
At each meeting, there will be a presenter who will be responsible for leading the discussion of a paper. The paper will be chosen by the presenter (possibly from paper stack below) and posted here about a week before the corresponding meeting. The presenter will not use any slides but can rely on the whiteboard to illustrate ideas, equations, etc. Participants should come to the meeting with the paper either printed out (double-sided!) or available on a portable device (laptop, iPad, etc). Participants are strongly encouraged to read the paper beforehand (they should have spent at least 1-2 hours to gain a basic understanding).
Here are some guidelines for the presenter, who should come to the meeting with answers to each of these questions.
1) What problem is the paper addressing? Is this an interesting mathematical problem? At a very high level, is this a classical mathematical problem? Are there classical solutions (e.g., something you can find on wikipedia) that you can think of?
2) What other state-of-the-art methods/algorithms (say published in last 3-5 years) are out there that address the same/similar problem? Do authors run benchmarking experiments (i.e. empirical comparisons)?
3) What is the application the authors choose (if any)? Is this an interesting application? What was lacking for existing solutions? Were they too slow? Maybe they didn’t really solve the problem exactly?
4) What’s wrong with the proposed method? What are the acknowledged/unacknowledged weaknesses?
5) How can the proposed method be improved? What are the natural future directions of research? Are there new applications you can think of?
6) What would you do differently if you approached this problem?
7) What is the core innovation and contribution of this paper? Is it a mathematical derivation? If so, can you point to it and understand the steps? Was there a far-reaching theoretical result/insight? If so, can you summarize? Was there a novel empirical finding? Is there an accompanying open software package that others can pick up and use on their own data/problem?
NEXT MEETING
Sep 14, 2023 Ben and Pranay SAM-Med2D
PAPER STACK
Z. Geng, Z. Lin, Is attention better than matrix decomposition?, ICLR 2021
R. Wang, C. Davatzikos, Bias in machine learning models can be significantly mitigated by careful training, PNAS 2022
C. Bass, E.C. Robinson, Icam-reg: Interpretable classification and regression with feature attribution for mapping neurological phenotypes in individual scans, IEEE TMI 2022
T. Fel, T. Serre, Harmonizing the object recognition strategies of deep neural networks with humans, NeurIPS 2022
Y. Kwon, J. Zou, WeightedSHAP: analyzing and improving Shapley based feature attributions, NeurIPS 2022
L. Moschella, E. Rodolà, Relative representations enable zero-shot latent space communication, 2022
A. Fawzi, P. Kohli, Discovering faster matrix multiplication algorithms with reinforcement learning, Nature 2022
M. Elbatel, A. Bria, Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images, MICCAI 2022 DART Workshop
L. Maier-Hein, P. F. Jager, Metrics reloaded: Pitfalls and recommendations for image analysis validation, 2022
D. Blalock, J. Guttag, Multiplying Matrices Without Multiplying, ICML 2021
M. Böhle, B. Schiele, B-cos Networks: Alignment is All We Need for Interpretability, CVPR 2022
Y. Wang, M. I. Jordan, Desiderata for Representation Learning: A Causal Perspective, 2022
A. P. Steiner, L. Beyer, How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers, TMLR 2022
S. Lotfi, A. G. Wilson, Bayesian Model Selection, the Marginal Likelihood, and Generalization, ICML 2022
M. Gordon, M. Bernstein, Jury learning: Integrating dissenting voices into machine learning models, CHI 2022
A. Zhmoginov, M. Vladymyrov, HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning, 2022
W. Liu, P. Fua, Leveraging Self-Supervision for Cross-Domain Crowd Counting, 2022
A. D. Desai, A. Chaudhari, SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluation, NeurIPS Datasets and Benchmarks, 2021.
E. Daxberger, P. Hennig, Laplace Redux--Effortless Bayesian Deep Learning, NeurIPS 2021.
J. von Oswald, B. F. Grewe, Continual learning with hypernetworks, ICLR 2020.
S. C. Huang, S. Yeung, GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition, ICCV 2021.
T. R. Shaham, T. Michaeli, Spatially-Adaptive Pixelwise Networks for Fast Image Translation, CVPR 2021.
P. Lippe, E. Gavves, Categorical Normalizing Flows via Continuous Transformations, ICLR 2021.
X. Chen, K. He, Exploring simple siamese representation learning, CVPR 2021.
Y. Song, B. Poole, Score-based generative modeling through stochastic differential equations, ICLR 2021.
K. Wang, M. Lustig, High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Loss, 2021.
M. Z. Darestani, R. Heckel, Measuring Robustness in Deep Learning Based Compressive Sensing, 2021.
W. Liu, Y. Li, Energy-based Out-of-distribution Detection, NeuRIPS 2020.
R. Liégeois, A. H. Sayed, Revisiting correlation-based functional connectivity and its relationship with structural connectivity, Network Neuroscience 2020.
O. S. Pianykh, J. A. Brink, Continuous Learning AI in Radiology: Implementation Principles and Early Applications, Radiology 2020.
M. Belkin, S. Mandal, Reconciling modern machine-learning practice and the classical bias–variance trade-off, PNAS 2019.
S. Farquhar, Y. Gal. "Towards Robust Evaluations of Continual Learning" arXiv preprint arXiv:1805.09733 (2018) link
H. Hassani, M. Soltanolkotabi, A. Karbasi. "Gradient Methods for Submodular Maximization" arXiv preprint arXiv:1708.03949 (2017) link
R. Kondor, S. Trivedi. "On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups" arXiv preprint arXiv:1802.03690 (2018) link
E. R. Elenberg, A. G. Dimakis, M. Feldman, A. Karbasi. "Streaming Weak Submodularity: Interpreting Neural Networks on the Fly" arXiv preprint arXiv:1703.02647 (2017) link
B. Zhu, J. Z. Liu, S. F. Cauley, B. R. Rosen, and M. S. Rosen. "Image reconstruction by domain-transform manifold learning." Nature. Mar 555(2018); 487-492 link
Z. C. Lipton, Y.-X. Wang, A. Smola. "Detecting and Correcting for Label Shift with Black Box Predictors" arXiv preprint arXiv:1802.03916 (2018) link
M. Johnson, D. K. Duvenaud, A. Wiltschko, R. P. Adams, and S. R. Datta. "Composing graphical models with neural networks for structured representations and fast inference." In Advances in neural information processing systems, pp. 2946-2954. (2016) link
C. Li, M. Z. Zia, Q.-H. Tran, X. Yu, G. D.Hager, M. Chandraker. "Deep Supervision with Intermediate Concepts" arXiv preprint arXiv:1711.11386 (2017) link
W. Wang, Y. Pu, V.K. Verma, K. Fan, Y. Zhang, C. Chen, P. Rai, and L. Carin. "Zero-Shot Learning via Class-Conditioned Deep Generative Models" arXiv preprint arXiv:1711.05820 (2017) link
A. N. Gomez, R. B. Grosse. The Reversible Residual Network: Backpropagation Without Storing Activations, 2017
R. Shwartz-Ziv, and N. Tishby. "Opening the Black Box of Deep Neural Networks via Information" arXiv preprint arXiv:1703.00810 (2017) link
Zhou, Jian, and Olga G. Troyanskaya. "Predicting effects of noncoding variants with deep learning-based sequence model." Nature methods 12.10 (2015): 931-934.
g-drive copy
PAST MEETINGS
July 5, 2023 Xuemin and Alan Uncalibrated Models Can Improve Human-AI Collaboration
June 28, 2023 Jacob and Raul Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images
June 21, 2023 Haomiao and Basar Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
June 14, 2023 Xinzi and Kenya Improving the accuracy of medical diagnosis with causal machine learning
June 7, 2023 Minh and Qin BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Model
May 22, 2023 Cagla and Nurislam Integral Neural Networks
Apr 25, 2023 Boqi and Lin Diagnosing and Rectifying Vision Models using Language
Apr 18, 2023 Yifeng and Mariia Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding
Apr 11, 2023 Chris and Pranay - Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Mar 28, 2023 Nurislam and Xuemin - KNN-Diffusion: Image Generation via Large-Scale Retrieval
Mar 21, 2023 Raul and Sara - f-SfT: Shape-From-Template With a Physics-Based Deformation Model
Feb 21, 2023 Ben and Alan Gradient Descent: The Ultimate Optimizer
Feb 07, 2023 Zijin and Peirong Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Jan 31, 2023 Minh and Basar Domain Adaptation under Open Set Label Shift
Jan 24, 2023 Kenya and Heejong Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
Jan 17, 2023 Xinzi and Qin Why do Nearest Neighbor Language Models Work?
Jan 10, 2023 Batuhan and Yining Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow
Dec 06, 2022 Qin and George Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
Nov 29, 2022 Alan and Mariia Diversify and Disambiguate: Learning From Underspecified Data
Nov 22, 2022 Yifeng and Pranay Robust continuous clustering
Nov 15, 2022 Chris and Xuemin Mitigating Neural Network Overconfidence with Logit Normalization
Nov 08, 2022 Zijin and Basar On feature learning in the presence of spurious correlations
Nov 01, 2022 Sara and Minh Interactive Classification by Asking Informative Questions, ACL 2020
Oct 25, 2022 Cagla and Yining GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
Oct 18, 2022 Boqi and Raul What Makes Transfer Learning Work for Medical Images: Feature Reuse & Other Factors
Oct 11, 2022 Lin and Sara Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning
Oct 03, 2022 Qin and Alan Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer, NIPS 2018
Sep 27, 2022 Minh and Basar Leveraging Time Irreversibility with Order-Contrastive Pre-training, AISTATS 2022
Sep 20, 2022 Heejong and Peirong Neural Additive Models: Interpretable Machine Learning with Neural Nets, 2022
Sep 13, 2022 Zijin and Kenya Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise, 2022
Sep 06, 2022 Batuhan and Xinzi Motion Correction and Volumetric Reconstruction for Fetal fMRI Data, NeuroImage 2022
Aug 30, 2022 Nurislam and Ben Elucidating the Design Space Of Diffusion-Based Generative Models, 2022
Aug 03, 2022 Cagla and Yining NICE-SLAM: Neural Implicit Scalable Encoding for SLAM, CVPR 2022
July 27, 2022 Zhenzhen and Christian GAN-Supervised Dense Visual Alignment, CVPR 2022
July 20, 2022 Heejong and Daniel Instant NGP, SIGGRAPH 2022
July 13, 2022 Hastings and Steffen Implicit Neural Representations for Deformable Image Registration, MIDL 2022
July 06, 2022 Xinzi and Qin A ConvNet for the 2020s, CVPR 2022
June 29, 2022 Raul and Cagla ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging, CVPR 2022
June 22, 2022 - Nurislam and Victor Robust and Efficient Medical Imaging with Self-Supervision, 2022
June 15, 2022 - Xinzi and Boqi Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning, 2022
June 8, 2022 - Ben and Yining High-Resolution Image Synthesis with Latent Diffusion Models, 2022
June 1, 2022 - Batuhan and Kenya Light-weight Deformable Registration using Adversarial Learning with Distilling Knowledge, 2021
May 12, 2022 - Victor and Tianyu Simplicial Embeddings in Self-Supervised Learning and Downstream Classification, 2022
May 5, 2022 - Batuhan and Zijin The Distributed Information Bottleneck reveals the explanatory structure of complex systems, 2022
Apr 28, 2022 - Gia and Ben ENHANCE (ENriching Health data by ANnotations of Crowd and Experts): A case study for skin lesion classification, MELBA 2021
Apr 14, 2022 - Alan and Zhilu PathologyGAN: Learning deep representations of cancer tissue, MIDL 2020
Mar 31, 2022 - Heejong and Batuhan Tutorial: Neural Tangent Kernel
Mar 24, 2022 - Xinzi and Sijia Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains, NeuRIPS 2020
Mar 17, 2022 - Ben and Victor Gradients without Backpropagation, 2022
Mar 10, 2022 - Alan and Minh VAE with a VampPrior, AISTATS 2018
Mar 03, 2022 - Zijin and Cagla Learning Multimodal VAEs through Mutual Supervision
Feb 24, 2022 - Tianyu and Minh Denoising Diffusion Probabilistic Models, 2020
Feb 17, 2022 - Xinzi DIFFUSEVAE: EFFICIENT, CONTROLLABLE AND HIGH-FIDELITY GENERATION FROM LOW-DIMENSIONAL LATENTS, 2022
Feb 03, 2022 - Ben and Zijin Long-range and hierarchical language predictions in brains and algorithms, 2021
Jan 26, 2022 - Heejong and Batuhan
Online / Offline Reinforcement Learning
Jan 19, 2022 - Gia and Minh
M. Fatemi et al, Medical Dead-ends and Learning to Identify High-risk States and Treatments, NeurIPS 2021.
Jan 12, 2022 - Heejong and Alan
S. Borgeaud et al, Improving language models by retrieving from trillions of tokens.
Jan 05, 2022 - Cagla and Zhilu
M. Naseer et al, Intriguing Properties of Vision Transformers, NeurIPS 2021.
Dec 08, 2021 - Sijia and Gia
A. Kendall et al, Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Dec 01, 2021 - Batuhan and Heejong
J. Lee et al, Learning Debiased Representation via Disentangled Feature Augmentation
Nov 17, 2021 - Zijin and Xinzi
K. He et al, Masked Autoencoders Are Scalable Vision Learners
Nov 10, 2021 - Victor and Tianyu
X. Liu et al, Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation
Nov 3, 2021 - Zhilu and Ben
J. Kossen et al, Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
October 27, 2021 - Mengying and Hao
V. Venkatraghavan et al, Disease progression timeline estimation for Alzheimer's disease using discriminative event based modeling
October 20, 2021 - Gia and Minh
F. Locatello et al, Challenging common assumptions in the unsupervised learning of disentangled representations
October 13, 2021 - Evan and Cagla
Baldock et al, Deep Learning Through the Lens of Example Difficulty
October 06, 2021 - Heejong and Tianyu
Wang et al, High-frequency Component Helps Explain the Generalization of Convolutional Neural Networks
September 29, 2021 - Zijin and Batuhan
Da Silva et al, Distinguishing Healthy Ageing from Dementia: a Biomechanical Simulation of Brain Atrophy using Deep Networks
September 22, 2021 - Minh and Sijia
Jabri et al, Space-time correspondence as a contrastive random walk
September 15, 2021 - Hao and Xinzi
Radford et al, Learning Transferable Visual Models From Natural Language Supervision
September 8, 2021 - Ben and Alan
Xiao et al, Early Convolutions Help Transformers See Better
September 1, 2021 - Victor and Zhilu
Raghu et al, Do Vision Transformers See Like Convolutional Neural Networks?
May 19, 2021 - Sijia and Jinwei
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks link
May 12, 2021 - Cagla and Zhilu
Differentiable Patch Selection for Image Recognition link
April 28, 2021 - Leo and Evan
Deep Double Descent: Where Bigger Models and More Data Hurt link
April 21, 2021 - Cagla and Tianyu
Zhan et al., Self-Supervised Scene De-occlusion link
April 14, 2021 - Hang and Zijin
Chen et al., Learning Continuous Image Representation with Local Implicit Image Function link
April 5, 2021 - Victor and Fayzan
Littwin et al., On Infinite-Width Hypernetworks link
March 31, 2021 - Bhargava and Meenakshi
Chami, Ines, et al., From trees to continuous embeddings and back: Hyperbolic hierarchical clustering link
March 24, 2021 - Amaya and Evan
D’Souza, Niharika Shimona, et al., A Deep-Generative Hybrid Model to Integrate Multimodal and Dynamic Connectivity for Predicting Spectrum-Level Deficits in Autism. link
Feb 17, 2021 - Leo Moon and Zhilu Zhang
Shen et al, 2020, Reservoir Transformers link
Feb 10, 2021 - Carmen and Tianyu
Carion et al, 2020, End-to-End Object Detection with Transformers link
Jan 27, 2021 - Zijin and Cagla
Brock, A., Donahue, J., & Simonyan, K., 2018, Large scale GAN training for high fidelity natural image synthesis. link
Jan 13, 2021 - Bhargava and Evan
Bianchi et al, 2020, Reservoir computing approaches for representation and classification of multivariate time series link
Dec 16 - Victor and Gia
Havasi et al, 2020, Training Independent Subnetworks for Robust Prediction link
Dec 9 - Zijin and Alan
Ponce et al, 2019, Evolving Images for Visual Neurons Using a Deep Generative Network Reveals Coding Principles and Neuronal Preferences link
Dec 2 - Tianyu and Meenakshi
Bear et al, 2020, Learning Physical Graph Representations from Visual Scenes
Nov 18 - Zhilu and Vic
Dosovitskiy et al, 2020, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
*Note: We will also be going through: Ashish Vaswani et al. 2017 as part of this paper.
Nov 4 - Evan and Sijia
Zhou et al, 2019, Models Genesis: Generic Autodidactic Modelsfor 3D Medical Image Analysis link
Oct 28, 2020 - Cagla and Bhargava
Kaiming He et al., 2015, Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, link
Oct 21, 2020 - Carmen and Zijin
Robert Tjarko Lange & Henning Sprekeler, 2020, LEARNING NOT TO LEARN: NATURE VERSUS NURTURE IN SILICO link
Oct 14, 2020 - Alan and Victor
Zhang et al., 2020, A Causal View on Robustness of Neural Networks, link
Oct 7, 2020
Vic and Tianyu will lead the discussion.
Blei et al., 2019.
"The Blessings of Multiple Causes"
link
Sept 30, 2020
Evan and Meenakshi will lead the discussion.
Maoz et al., 2020.
"Learning probabilistic neural representations with randomly connected circuits"
link
Sept 23, 2020
Cagla and Gia will lead the discussion.
Tokunaga 2019.
"Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology"
link
Sept 16, 2020
Bhargava and Tianyu will lead the discussion.
Inoue.
"Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence Level"
[http://proceedings.mlr.press/v89/inoue19a.html]
Sept 2, 2020
Victor and Zhilu will lead the discussion.
Dusenberry et al.
"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors" ICML 2020.
link
August 26, 2020
Alan and Zijin will lead the discussion.
Lunz et al.
"Adversarial Regularizers in Inverse Problems." NeurIPS 2018.
link
August 19, 2020
Meenakshi and Carmen will lead the discussion.
Alcorn et al.
"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects." CVPR 2019.
link
August 12, 2020
Gia and Evan will lead the discussion.
Corneanu et al.
“Computing the Testing Error without a Testing Set." CVPR 2020
link
August 5, 2020
Bhargava and Vic will lead the discussion.
Lin et al.
“Visual Chirality"
[https://arxiv.org/pdf/2006.09512.pdf]
July 29, 2020
Zijin and Tianyu will lead the discussion.
W Van Gansbeke et al.
“SCAN: Learning to Classify Images without Labels."
[https://arxiv.org/pdf/2005.12320.pdf]
July 22, 2020
Alan and Carmen will lead the discussion.
Robey et al.
“Model-Based Robust Deep Learning."
[https://arxiv.org/pdf/2005.10247.pdf]
July 15, 2020
Meenakshi and Sijia will lead the discussion.
Sinz et al.
“Stimulus domain transfer in recurrent models for large scale cortical prediction on video." NeurIPS 2018.
[https://papers.nips.cc/paper/7950-stimulus-domain-transfer-in-recurrent-models-for-large-scale-cortical-population-prediction-on-video.pdf]
July 8, 2020
Gia will lead the discussion.
Bica et al.
“Estimating Counterfactual Treatment Outcomes Over Time Through Adversarially Balanced Representation." ICLR2020.
[https://openreview.net/pdf?id=BJg866NFvB]
July 1, 2020
Victor will lead the discussion.
Joel Dapello et al.
“Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations." bioRxiv.
[https://www.biorxiv.org/content/10.1101/2020.06.16.154542v1]
June 17, 2020
Evan will lead the discussion.
J. R. Clough et al.
“Explicit topological priors for deep-learning based image segmentation using persistent homology." IPMI 2019.
link
May 27, 2020
Artem will lead the discussion.
"Neurovolution of Self-Interpretable Agents"
Tang, Yujing; Nguyen, Duong; Ha, David. GECCO 2020
link
May 13, 2020
Carmen will lead the discussion.
"Interpretable deep neural network for cancer survival analysis by integrating genomic and clinical data"
Hao et al.
link
April 29, 2020
Victor will lead the discussion.
"Causality for Machine Learning"
Bernhard Schölkopf
link
April 22, 2020
Zhilu will lead the discussion.
"Your classifier is secretly an energy based model and you should treat it like one"
Grathwohl et al.
link
April 12, 2020
Meenakshi will lead the discussion.
"Towards a deep network architecture for structured smoothness"
Habeeb et al.
link
April 8, 2020
Zijin will lead the discussion.
"Metric learning with spectral graph convolutions on brain connectivity networks"
Ktena et al.
link
April 1, 2020
Evan will lead the discussion.
"Restricting the Flow: Information Bottlenecks for Attribution"
Schulz et al.
link
March 25, 2020
Alan will lead the discussion.
"Inference Suboptimality in Variational Autoencoders"
C. Cremer et al.
link
March 11, 2020
Carmen will lead the discussion.
"Deep learning with multimodal representation for pancancer prognosis prediction"
Anika Cheerla and Olivier Gevaert.
link
March 4, 2020
Zhilu will lead the discussion.
"How Good is the Bayes Posterior in Deep Neural Networks Really?"
F. Wenzel et al.
link
February 12, 2020
Matthew will lead the discussion.
"Counterfactual Normalization: Proactively Addressing Dataset Shift and
Improving Reliability Using Causal Mechanisms"
A. Subbaswamy and S. Saria
link
February 5, 2020
Gia will lead the discussion.
"Causality matters in medical imaging"
arxiv link
January 29, 2020
Victor will lead the discussion.
"Stand-Alone Self-Attention in Vision Models"
arxiv link
January 22, 2020
Artem will lead the discussion.
Nabil Imam and Thomas A Cleland, "Rapid online learning and robust recall in a neuromorphic olfactory circuit"
arxiv link
December 11, 2019
Zijin will lead the discussion.
M. Zhang, Z. Cui, M. Neumann, and Y. Chen, "An End-to-End Deep Learning Architecture for Graph Classification" (AAAI-18).
link Supplementary Material
November 13, 2019
Sijia will lead the discussion.
Chambon, Stanislas, Valentin Thorey, Pierrick J. Arnal, Emmanuel Mignot, and Alexandre Gramfort
"A Deep Learning Architecture to Detect Events in EEG Signals During Sleep".
link
October 30, 2019
Zhilu will lead the discussion.
Maximilian Ilse, Jakub M. Tomczak, Max Welling "Attention-based Deep Multiple Instance Learning" (ICML 2018).
link
October 16, 2019
Artem will lead the discussion.
Rosenbaum, Cases, Riemer, Klinger "ROUTING NETWORKS AND THE CHALLENGES OF MODULAR AND COMPOSITIONAL COMPUTATION" (2019). link
code and related work
September 25, 2019
Carmen will lead the discussion.
Gao et al. "Distanced LSTM: Time-Distanced Gates in Long Short-Term Memory Models for Lung Cancer Detection" (2019). link
September 18, 2019
Meenakshi will lead the discussion.
Beliy et al. "From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI" (2019). pdf link
September 11, 2019
Artem will lead the discussion.
Kelvin Xu et. al.
"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention" link
Pytorch implementation: link
Relevant natural language translation predecessor (Bahdanaue et. al., 2014): paper (link), and pytorch (link)
September 4, 2019
Matt will lead the discussion.
Taco S. Cohen, Max Welling
"Group Equivariant Convolutional Networks" link
June 19, 2019
Meenakshi will lead the discussion.
Taco S. Cohen, Mario Geiger, Jonas Koehler, Max Welling
"Spherical CNNs" link
June 12, 2019
Tianyu will lead the discussion.
Mingxing Tan, Quoc V. Le
"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks" (2019) link
June 5, 2019
Sijia will lead the discussion.
Aitchison et al.
"Model-based Bayesian inference of neural activity and connectivity from all-optical interrogation of a neural circuit" link
May 29, 2019
Gia will lead the discussion.
Kirschbaum, et al. "LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos" link
May 22, 2019
Carmen will lead the discussion.
Li, Dan, et al. "Bayesian latent time joint mixed effect models for multicohort longitudinal data." link
May 15, 2019
Evan will lead the discussion.
Ilyas, Andrew, et al. "Adversarial Examples Are Not Bugs, They Are Features." link
May 8, 2019
Matthew will lead the discussion.
Somayyeh Soltanian-Zadeha, Kaan Sahingura, Sarah Blaua, Yiyang Gonga, and Sina Farsiu
"Fast and robust active neuron segmentation in twophoton calcium imaging using spatiotemporal deep learning"
PNAS 2019. [https://www.pnas.org/content/116/17/8554]
April 29, 2019
Adrian will lead the discussion.
"Semi-Supervised and Task-Driven Data Augmentation"
Krishna Chaitanya, Neerav Karani, Christian Baumgartner, Olivio Donati, Anton Becker, Ender Konukoglu
IPMI 2019. [https://arxiv.org/abs/1902.05396]
April 17, 2019
Artem will lead the discussion.
Mnih, Andriy, and Danilo J. Rezende. "Variational Inference for Monte Carlo Objectives." link
Appears in Proceedings of the 33rd International Conference on Machine Learning (ICML), New York, NY, USA, 2016. JMLR: W&CP volume 48
April 11, 2019
Gia will lead the discussion.
Schulam, P. and Saria, S. (2017). Reliable decision support using counterfactual models. In Advances in Neural Information Processing Systems (pp. 1697-1708). link
March 27, 2019
Mohammad will be leading the discussion.
Roy, A. G., Siddiqui, S., Pölsterl, S., Navab, N., & Wachinger, C. (2019). 'Squeeze & Excite'Guided Few-Shot Segmentation of Volumetric Images. arXiv preprint arXiv:1902.01314. link
March 6, 2019
Elvisha will be leading the discussion.
Fong, R. C., Scheirer, W. J., & Cox, D. D. (2018). Using human brain activity to guide machine learning. Scientific reports, 8(1), 5397.
[https://www.nature.com/articles/s41598-018-23618-6]
Feb 27, 2019
Jiahao will lead the discussion
Wang, Tongzhou, Jun-Yan Zhu, Antonio Torralba, and Alexei A. Efros. "Dataset Distillation." arXiv preprint arXiv:1811.10959(2018).
[https://arxiv.org/abs/1811.10959]
Feb 13, 2019
Cagla will lead the discussion
VAE-GANs for Probabilistic Compressive Image Recovery: Uncertainty Analysis
Vineet Edupuganti, Morteza Mardani, Joseph Cheng, Shreyas Vasanawala, John Pauly
[https://arxiv.org/abs/1901.11228v1]
Feb 6, 2019
Evan will lead the discussion
Moyer, Daniel, et al. "Invariant Representations without Adversarial Training." Advances in Neural Information Processing Systems. 2018.
[https://arxiv.org/abs/1805.09458]
Jan 30, 2019
Yingying zhu will lead the discussion.
Suwajanakorn, et al. Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
[https://arxiv.org/abs/1807.03146]
Jan 23, 2019
Artem will lead the discussion
Grathwohl, Will, et al. "Ffjord: Free-form continuous dynamics for scalable reversible generative models." arXiv preprint arXiv:1810.01367 (2018)
[https://arxiv.org/abs/1810.01367]
Jan 4, 2019
Adrian will lead the discussion
Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud
"Neural Ordinary Differential Equations"
Dec 14, 2018
Gia will lead the discussion
Wu, Mike et al. "Beyond Sparsity: Tree Regularization of Deep Models for Interpretability" link
Nov 21, 2018
Evan will lead the discussion
Kohl, Simon AA, et al. "A Probabilistic U-Net for Segmentation of Ambiguous Images." link
Nov 14, 2018
Matthew will lead the discussion (section 3.2 to end)
J. Pearl, "Causal inference in statistics: An overview" UCLA Cognitive Systems Laboratory, Technical Report (R-350), September 2009. Statistics Surveys, Vol. 3, 96—146, 2009. link
Nov 7, 2018
Matthew will lead the discussion (through section 3.1)
J. Pearl, "Causal inference in statistics: An overview" UCLA Cognitive Systems Laboratory, Technical Report (R-350), September 2009. Statistics Surveys, Vol. 3, 96—146, 2009. link
Oct 31, 2018
Adrian will lead the discussion
Joshi, Sarang, et al. "Unbiased diffeomorphic atlas construction for computational anatomy." NeuroImage 23 (2004): S151-S160. link
Oct 16, 2018
Mohammad will lead the discussion
Shah, Meet P., S. N. Merchant, and Suyash P. Awate. "MS-Net: Mixed-Supervision Fully-Convolutional Networks for Full-Resolution Segmentation." International Conference on Medical Image Computing and Computer-Assisted Intervention (2018). link
Oct 3, 2018
Zhilu will lead the discussion
Alemi, Alexander, et al. "Fixing a Broken ELBO." International Conference on Machine Learning. 2018. link
September 26, 2018
Evan will lead the discussion
Adebayo, Julius, et al. "Local explanation methods for deep neural networks lack sensitivity to parameter values." (2018). link
September 12, 2018
Meenakshi will lead the discussion
A. Zhitnikov, R. Mulayoff, T. Michaeli. "Revealing common statistical behaviors in heterogeneous populations". Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5950-5959, 2018. link
September 5, 2018
Gia will lead the disussion
A. Mensch, J. Mairal, D. Bzdok, B. Thirion, G. Varoquaux. "Learning Neural Representations of Human Cognition across Many fMRI Studies" arXiv preprint arXiv:1710.11438 link
August 22, 2018
Artem will lead the discussion
D. P. Kingma, P. Dhariwal. "Glow: Generative Flow with 1x1 Convolutions" arXiv preprint arXiv:1807.03039 (2018) link
Background Reading which might be useful, which first introduced Flow-based density estimation:
Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio. "Density estimation using Real NVP" arXiv preprint arXiv:1605.08803 (2016) link
June 20, 2018
Sundaresh will lead the discussion.
H. K. Aggarwal, M. P. Mani, M. Jacob. "MoDL: Model Based Deep Learning Architecture for Inverse Problems" arXiv preprint arXiv:1712.02862 (2017) link
June 13, 2018
Artem and Jinwei will lead the discussion
J. P. Haldar, D. Kim. "OEDIPUS: An Experiment Design Framework for Sparsity-Constrained MRI" arXiv preprint arXiv:1805.00524 (2018) link
June 6, 2018
Cagla will lead the discussion
A. Loktyushin, H. Nickisch, R. Pohmann, B. Schölkopf. "Blind retrospective motion correction of MR images" Magnetic Resonance in Medicine. 2013 Dec 11; 70(6): 1608–1618. link
May 30, 2018
Sundaresh will lead the discussion
H. Zhang, I. Goodfellow, D. Metaxas, A. Odena. "Self-Attention Generative Adversarial Networks" arXiv preprint arXiv:1805.08318 (2018) link
We will skip May 23, 2018 as Mert is out of town.
We will skip May 16, 2018 as Mert is busy.
We will skip May 9, 2018 as Mert is out of town.
May 2, 2018
Adrian will lead the discussion
D. P. Kingma, J. Ba. "Adam: A Method for Stochastic Optimization" arXiv preprint arXiv:1412.6980 (2014) link
April 25, 2018
Meenakshi will lead the discussion
L. M. Zintgarf, T. S. Cohen, T. Adel, M. Welling. "Visualizing Deep Neural Network Decisions: Prediction Difference Analysis" arXiv preprint arXiv:1702.04595 (2017) link
We will skip April 18, 2018 as Mert is busy.
We will skip April 11, 2018 as Mert is out of town.
We will skip April 4, 2018 on account of spring break.
We will skip March 28, 2018 as Mert is out of town.
March 21, 2018
Sundaresh will lead the discussion.
D. M. Pelt and J. A. Sethian "A mixed-scale dense convolutional neural network for image analysis" Proceedings of the National Academy of Sciences (2017): p.201715832 link
We will skip March 14, 2018 as Mert is busy.
We will skip March 7, 2018 as Mert is unavailable.
February 28, 2018
Evan will lead the discussion.
X. Chen, D. P. Kingma, T. Salimans, Y. Duan, P. Dhariwal, J. Schulman, I. Sutskever, P. Abbeel. "Variational Lossy Autoencoder" arXiv preprint arXiv:1611.02731 (2016) link
We will skip February 21, 2018 as Mert is busy.
February 14, 2018
Zhilu will lead the discussion.
H. Noh, T. You, J. Mun, and B. Han. "Regularizing deep neural networks by noise: its interpretation and optimization" arXiv preprint arXiv:1710.05179 (2017) link
We will skip February 7, 2018 due to snow storm
January 31, 2018
Adrian will lead the discussion.
W. Wang, R. Arora, K. Livescu, and J. Blimes "On Deep Multi-View Representation Learning" Proceedings of International Conference on Machine Learning (2015) link
January 24, 2018
Cagla will lead the discussion.
K. C. Tezcan, C. F. Baumgartner, and E. Konukoglu. "MR image reconstruction using the learned data distribution as prior" arXiv preprint arXiv:1801.03399 (2018) link
We will skip January 17, 2018 as Mert is busy.
January 10, 2018
Mohammad will lead the discussion.
D. L. K. Yamins and J. D. DiCarlo "Using goal-driven deep learning models to understand sensory cortex" Nature Neuroscience 19, pp.356–365 (2016) link
December 13, 2017
James will lead the discussion.
S. Sabour, N. Frosst, G. E. Hinton. "Dynamic Routing Between Capsules" arXiv preprint arXiv:1710.09829 (2017). link
R. Girshick. "Fast R-CNN." arXiv preprint arXiv:1504.08083 (2015). link
December 6, 2017
Yingying will lead the discussion.
K. He, G. Gkioxari, P. Dollár, R. Girshick. "Mask R-CNN." arXiv preprint arXiv:1703.06870 (2017). link
We will skip November 29, 2017 as Mert is not here.
Novermber 22, 2017
No journal club due to Thanksgiving break
November 15, 2017
Evan and Sundaresh will lead the discussion.
Mescheder, Lars, Sebastian Nowozin, and Andreas Geiger. "Adversarial variational bayes: Unifying variational autoencoders and generative adversarial networks." arXiv preprint arXiv:1701.04722 (2017). link
November 8, 2017
Meenakshi will lead the discussion.
S. Parisot, S. I. Ktena, E. Ferrante, M. Lee, R. M. Moreno, B. Glocker, and D. Rueckert. "Spectral Graph Convolutions for Population-based Disease Prediction" arXiv preprint arXiv:1703.03020 (2017) link
We will skip November 1, 2017 as Mert is not here.
October 25, 2017
Jinwei will lead the discussion.
K. Kamnitsas, C. Ledig, V. F. J. Newcombe, J. P. Simpson, A. D. Kane, D. K. Menon, D. Reuckert, and B. Glocker. "Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation." Medical Image Analysis. Feb 36(2017); 61-78 link
P. Krahenbuhl and V. koltun. "Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials." arXiv preprint arXiv:1210.5644 (2012) link
October 18, 2017
Sundaresh will lead the discussion.
Stéphane Mallat. "Understanding deep convolutional networks." Phil. Trans. R. Soc. A 374.2065 (2016): 20150203. link
October 11, 2017
Cagla will lead the discussion.
D. Ma, V. Gulani, N. Sieberlich, K. Liu, J. L. Sunshine, J. L. Duerk, and M. A. Griswold. "Magnetic resonance fingerprinting." Nature. 2013 Mar 14; 495(7440): 187–192. link
October 04, 2017
Yingying will lead the discussion.
P. Ji, T. Zhang, H. Li, M. Salzmann, and I. Reid. "Deep Subspace Clustering Networks." arXiv preprint arXiv:1709.02508 (2017) link
We will skip September 27, 2017 as Mert is not here.
September 20, 2017
Evan will lead the discussion.
Zhao, Mingmin, et al. "Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture." International Conference on Machine Learning. 2017. link
We will skip September 13, 2017 as Mert, Evan and Zhilu are at MICCAI.
September 6, 2017
Mert will lead the discussion.
Zhu, Jun-Yan, et al. "Unpaired image-to-image translation using cycle-consistent adversarial networks." arXiv preprint arXiv:1703.10593 (2017). link
June 14, 2017
Evan will lead the discussion.
"Understanding deep learning requires rethinking generalization" C Zhang, S Bengio, M Hardt, B Recht, O Vinyals - arXiv preprint arXiv:1611.03530, 2016
June 7, 2017
Mohammad will lead the discussion.
"Spatial Transformer Networks." M Jaderberg, K Simonyan, A Zisserman, K Kavukcuoglu. NIPS 2015
May 31, 2017
Zhilu will lead the discussion.
Doersch, Carl. "Tutorial on variational autoencoders." arXiv preprint arXiv:1606.05908 (2016).pdf link
May 3, 2017
Evan will lead the discussion.
"Generative adversarial nets." In Advances in neural information processing systems Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y., 2014 (pp. 2672-2680). pdf link
April 26, 2017
Mert will lead the discussion.
Chapters 1 and 2 of Andrew Wilson's PhD thesis. link
April 19, 2017
Evan will lead the discussion.
Rasmussen, Carl Edward. "Gaussian processes for machine learning." (2006). pdf link
April 12, 2017
No meetings as Mert's in NYC
April 5, 2017
No meeting as it's spring break.
First Meeting
March 29, 2017
Zhilu will lead the discussion.
Gal, Yarin, Riashat Islam, and Zoubin Ghahramani. "Deep Bayesian Active Learning with Image Data." arXiv preprint arXiv:1703.02910 (2017). arxiv link