A Gradient Flow Framework For Analyzing Network Pruning

Recent network pruning methods focus on pruning models early-on in training. To estimate the impact of removing a parameter, these methods use importance measures that were originally designed for pruning trained models… Despite lacking justification for their use early-on in training, models pruned using such measures result in surprisingly minimal accuracy loss. To better explain this behavior, we develop a general, gradient-flow based framework that relates state-of-the-art importance measures through an order of time-derivative of the norm of model parameters. […]

Read more

Scalable Recommendation of Wikipedia Articles to Editors Using Representation Learning

Wikipedia is edited by volunteer editors around the world. Considering the large amount of existing content (e.g. over 5M articles in English Wikipedia), deciding what to edit next can be difficult, both for experienced users that usually have a huge backlog of articles to prioritize, as well as for newcomers who that might need guidance in selecting the next article to contribute… Therefore, helping editors to find relevant articles should improve their performance and help in the retention of new […]

Read more

Grounded Compositional Outputs for Adaptive Language Modeling

Language models have emerged as a central component across NLP, and a great deal of progress depends on the ability to cheaply adapt them (e.g., through finetuning) to new domains and tasks. A language model’s emph{vocabulary}—typically selected before training and permanently fixed later—affects its size and is part of what makes it resistant to such adaptation… Prior work has used compositional input embeddings based on surface forms to ameliorate this issue. In this work, we go one step beyond and […]

Read more

Secure Data Sharing With Flow Model

In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training purposes, but the data are also encrypted so that they cannot be recovered by other parties… We present a rotation based method using flow model, and theoretically justified its security. We demonstrate the effectiveness of our method in different scenarios, including supervised secure model […]

Read more

Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences

Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a relevance ranking task, and fine-tune BERT on sequence-pair ranking task to select the most probable sense definition given a context sentence and a list of candidate sense definitions… We also introduce a data augmentation technique for WSD using existing example sentences from WordNet. […]

Read more

Presenting HackLive – A Guided Community Hackathon by Analytics Vidhya’s Data Science Experts!

“There is no alternative to learning through experience.” This quote rings true for every aspect of our life. And it takes on a whole new meaning in data science. Data Science hackathons area great way to: Test your data science knowledge Compete against top data science experts from around the world and gauge where you stand Get hands-on practice of a data science problem working in a deadline environment Improve your existing data science skillset Enhance your existing data science […]

Read more

10 Statistical Functions in Excel every Analytics Professional Should Know

Overview Microsoft Excel is an excellent tool for learning and executing statistical functions Here are 12 statistical functions in Excel that you should master for a successful analytics career   Let’s Excel in Statistics! “Statistics is the grammar of Science.” – Karl  Pearson Let’s make that a bit more relevant for us – Statistics is the grammar of “Data” Science. You’ll notice that almost every successful data science professional or analytics professional has a solid understanding of statistics – but […]

Read more

What is AWS? Why Every Data Science Professional Should Learn Amazon Web Services

Overview Amazon Web Services (AWS) is the leading cloud platform for deploying machine learning solutions Every data science professional should learn how AWS works   Introduction “Your machine ran out of memory.” Sounds familiar? It certainly is for me – especially anytime I try to run a complex machine learning algorithm on my personal machine. It’s quite a frustrating experience that a lot of data science professionals feel. We don’t have the unlimited computing power of the tech behemoths – […]

Read more

A Quick History of Neural Networks

This article is part of the Data Science Blogathon. Introduction Neural networks are ubiquitous right now. Organizations are splurging money on hardware and talent to ensure they can build the most complex neural networks and bring out the best deep learning solutions. Although Deep Learning is a fairly old subset of machine learning, it didn’t get its due recognition until the early 2010s. Today, it has taken the world by storm and captured public attention in a way that very […]

Read more

How I Became a Data Science Competition Master from Scratch

Overview Winning data science competitions can be a complex process – but you can crack the top 3 if you have a framework to follow Hear from a top data science hackathon expert and how he went from scratch to winning data science competitions   Introduction There is no alternative to learning through experience. Especially in the data science industry! I recently won the top prize in Zindi’s Zimnat Insurance Recommendation challenge – an achievement that ranks top among my […]

Read more
1 756 757 758 759 760 906