Paper: https://link.springer.com/article/10.1007/s10994-017-5633-9

Discussion led by Peter Husisian & Julia Allen, Intelligent Systems Subteam

Paper Objective

  • Utilize the incredible speed-up (800 billion factor) in mixed-integer optimization enabled by hardware improvements (Although they were deemed too expensive to be practical in the past, the paper shows that these methods are practically solvable on real-world datasets and even outperform classification and regression trees (CART))

A decision tree is a flowchart-like structure where every node represents a “test” on an attribute, each branch represents the outcome of a test, and each leaf node represents a class label, or the decision taken after considering all attributes.

Because…


Paper: https://openaccess.thecvf.com/content_CVPR_2019/papers/Kornblith_Do_Better_ImageNet_Models_Transfer_Better_CVPR_2019_paper.pdf

Discussion led by Stephen Tse & Felix Hohne, Intelligent Systems Subteam

Paper Objective

It is often implicitly assumed that models which perform well on ImageNet would perform better in other CV tasks as well. This paper looks to empirically investigate if it is true that models trained on ImageNet perform better on other CV datasets because they have been trained on ImageNet, or simply because their architectures are well suited for general CV tasks. More broadly, this paper discusses if CV is overfitting to the ImageNet dataset.

Background

The background of the paper consists of basic fundamental knowledge of modern computer…


Paper: https://arxiv.org/pdf/2008.10546.pdf

Discussion led by Phillip Si & Melinda Fang, Intelligent Systems subteam

Objectives of the Paper

Three sentence paper summary: Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scalable to modern deep neural nets. We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective.

Deep learning techniques have demonstrated high performance on numerous tasks, but recent research on adversarial networks and neural network stability have demonstrated that these models can unexpectedly fail, making current neural networks difficult to deploy in high…


Paper: https://arxiv.org/pdf/2010.11929.pdf

Discussion led by Victor Butoi & Cora Wu, Intelligent Systems subteam

Objectives of the Paper

What problem is the paper tackling?
Image Recognition at Scale tries to tackle the issue of applying Transformer architecture to Computer Vision tasks to lessen the field’s heavy reliance on CNNs. The paper makes the argument that this transition would produce comparable results to traditional CNNs while requiring less computational resources to train.

What is the relevant background for this problem?
Transformers have been used extensively for NLP tasks, such as the current state-of-the-art models BERT, GPT, and their variations. …


Paper: https://arxiv.org/pdf/2004.10934.pdf

Discussion led by Katie Yang, Evelyn Wu, and Wendy Huang, Intelligent Systems subteam

Objectives of the Paper

  • Develop a real-time object detection that can be trained on a standard GPU. They explore the performance and speed tradeoffs of appending new features such as mosaic data augmentation, Mish-activation, and DropBlock regularization of the YOLO v3 architecture, modified to accommodate these new features. YOLOv4 wants to achieve high accuracy and perform real-time detection, as most of the accurate models are not real-time.
  • Test out a wide variety of new features and their combinations that are proclaimed to be able to enhance CNN accuracy on…

Paper: https://arxiv.org/pdf/1704.04861.pdf

Discussion led by Felix Hohne & Evelyn Wu, Intelligent Systems subteam

Introduction

In order to increase model accuracy, data scientists often continuously increase the size of models. However, this comes at the expense of efficiency and computational hardware requirements. As a result, these oversized models may become unsuitable for some tasks. Self-driving cars, for example, need to identify problems quickly, or else their systems may not have enough time to resolve them, which can be very dangerous. The goal of this paper is to develop smaller, thinner CNNs that can perform comparably to larger models while still being lightweight…


Paper: https://arxiv.org/pdf/1803.03635.pdf

Discussion led by Peter Husisian & Phillip Si, Intelligent Systems subteam

Objectives/ Goals of the Paper

What problem is the paper tackling?

In Machine Learning, pruning techniques that remove unnecessary parameters are used in neural networks to improve speed and decrease model size without materially affecting accuracy. Earlier work has demonstrated that removing up to 90% of model parameters is possible without reducing accuracy, dramatically speeding up inference once the model is trained. However, up to this point, these models have not been very accurate to train with. The paper’s main contribution is finding a sparse representation of dense neural networks, which improves computational efficiency and generalization. …


Paper: https://arxiv.org/pdf/1906.06725.pdf

Discussion led by Cora Wu & Winnie Chow, Intelligent Systems subteam

Objectives / Goals of the Paper

The main objective of this paper is to develop the foundations for personalized persuasive conversational agents to change people’s opinions and actions for social good. In the paper, the authors create a classifier to predict persuasive strategies as the groundwork for future research in this area. Although there have already been previously published papers looking into learning better negotiation strategies, Persuasion for Good distinguishes itself through its emphasis on the personalization aspect of the persuasion process. …


Discussion led by Katie Yang & Stephen Tse, Intelligent Systems subteam

Objectives / Goals of the Paper

NLP models have become increasingly complex in the last decade, with GPT, GPT-2, BERT, and GPT-3 using ever more parameters and computational power. GPT-3, the current SOTA model from Open-AI, has 185 billion parameters and cost $5 million to train, far more than is feasible for all but the largest industrial research labs. The constant drive for increased accuracy, fostered in part by the ubiquitous use of leaderboards in NLP, has meant that other important factors for practical model use have been neglected. Leaderboards measure the performance of a…


By Danny Yang, Insights Subteam

One of the biggest challenges for people new to data science is finding the right dataset to use. There are a lot of online sources for data these days: from online collections found on sites like Kaggle to government and nonprofit open data APIs. The documentation on many datasets is lacking or inconsistent, and many beginners don’t know what questions to ask when evaluating whether a dataset should be used.

Recently, there has been a push to set industry standards for documenting datasets. …

Cornell Data Science

Cornell Data Science is an engineering project team @Cornell that seeks to prepare students for a career in data science.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store