Creating Deeper Bottleneck ResNet from Scratch using Tensorflow

We will see how to implement ResNet50 from scratch using Tensorflow 2.0 Figure 1. Residual Blocks and Skip Connections (Source: Image created by author) It is seen that often deeper neural networks perform better than shallow neural networks. But, deep neural networks face a common problem, known as the ‘Vanishing/Exploding Gradient Problem’. To overcome this … Read more

BERT: Why it’s been revolutionizing NLP

What’s so great about BERT? For me, there are three main things that make BERT so great. Number 1: pre-trained on a lot of data. Number 2: accounts for a word’s context. Number 3: open-source. Let’s discuss. #1: BERT is pre-trained on an absurd amount of data. The original BERT model comes in two sizes: … Read more

Machine Learning & Image to Audio Captioning

A brief literature review of how machine learning is used to translate images directly into speech. Machine learning (ML) has spread into many different fields and disciplines. Dipping your toes into a new field is the best way to grow and learn new things. The following is a summary of how researchers have applied machine … Read more

A Visual Guide to Random Forests

An intuitive visual guide and video explaining a powerful ensembling method One of the most deceptively obvious questions in machine learning is “are more models better than fewer models?” The science that answers this question is called model ensembling. Model ensembling asks how to construct aggregations of models that improve test accuracy while reducing the … Read more

Evaluate your model properly

It’s not all about the statistics The progress we are seeing in machine learning is undeniable, in any given week, we see new algorithms being researched and theorised, new libraries being released to the open-source community and new accuracy benchmarks being eclipsed. There is no doubt that the data science community are producing tools that … Read more

Bias in Natural Language Processing (NLP): A Dangerous But Fixable Problem

Now if you’re anything like me, you’re probably thinking: But how can machines be biased if they don’t have emotions? The key is that machine learning models learn patterns in the data. So let’s say our data tends to put female pronouns around the word “nurse” and male pronouns around the word “doctor.” Our model … Read more

Adversarially-Trained Classifiers for Generalizable Real World Applications

CS282A Designing and Understanding Neural Networks at UC Berkeley Photo by Kevin Ku on Unsplash The field of computer vision continuously calls for improved accuracy on classifiers. Researchers everywhere are trying to beat the previous benchmark by just some small margins on one particular dataset. We think this trend is great for pushing the edge … Read more

A Comprehensive Guide to Working With Recurrent Neural Networks in Keras

We will be training a recurrent neural network to predict Amazon stock prices. We can collect this from the pandas_datareader. The stock data is stored into a DataFrame named df. We’ll predict the closing prices, which can be accessed in the Close column. These prices will be separated into a training set and a testing … Read more

Sequence Unpacking in Python

Sequence unpacking in python allows you to take objects in a collection and store them in variables for later use. This is particularly useful when a function or method returns a sequence of objects. In this post, we will discuss sequence unpacking in python. Let’s get started! A key feature of python is that any … Read more

Support Vector Machine | Abhishek Kumar

In a practical scenario data is not as simple as to fit a linear decision boundary to it. Take a look at the following data set — Data set used for SVM model. Data set with a non linear decision boundary. Using line as a decision boundary is definitely a bad choice for the data set. … Read more

Time Series in 5-Minutes, Part 5: Anomaly Detection

[This article was first published on business-science.io, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. Have 5-minutes? Then let’s learn time series. In this short articles series, I … Read more

Categories R Tags ExcerptFavorite

AWS announces a 86%+ price reduction for AWS IoT Events

Today, we are reducing the price of AWS IoT Events by at least 86%. AWS IoT Events is a fully managed service that makes it easy to detect and respond to changes indicated by IoT sensors and applications. For example, you can use AWS IoT Events to detect malfunctioning machinery, a stuck conveyor belt, or … Read more

Categories AWS ExcerptFavorite

Pruning Neural Networks

Rather than just weights, activations on training data can be used as a criteria for pruning. When running a dataset through a network, certain statistics of the activations can be observed. You may observe that some neurons always outputs near-zero values. Those neurons can likely be removed with little impact on the model. The intuition … Read more

Train and analyze many models for #TidyTuesday crop yields

[This article was first published on rstats | Julia Silge, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. Lately I’ve been publishingscreencasts demonstrating how to use thetidymodels framework, … Read more

Categories R Tags ExcerptFavorite

How to Clean Data: {janitor} Package

[This article was first published on Exploring Data, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. Exploring-Data is a place where I share easily digestible content aimed at … Read more

Categories R Tags ExcerptFavorite

Time Series Smoothing for Better Clustering

In time series analysis, the presence of dirty and messy data can alter our reasonings and conclusions. This is true, especially in this domain, because the temporal dependency plays a crucial role when dealing with temporal sequences. Noise or outliers must be handled with care following ad-hoc solutions. In this situation, the tsmoothie package can … Read more

Optimizing Starbucks App Offers

We will now use the customer spending trends identified in our analyses to build a model that predicts whether a user will respond to an offer. The process of sending promotions to users requires labor and is a cost to the organization. If Starbucks implements a prediction model, they can alleviate these resources, while ensuring … Read more

GPT-3: Just Another Language Model But Bigger

Understanding the GPT-3 research paper GPT-3 has takeover the NLP world in a very short period of time. It has proved the theory that increasing number of parameters will increase the accuracy of model. Tweet by Sam Altman, Public Domain Created by Author on befunky Language model tries to predict the next word given the … Read more

Stack and Array Implementation with Python and NodeJs

Image by author We were discussed basic definitions of the Data structures and algorithms in the previous article. in this article, let’s dig deeper into the Data structure world, and especially, let’s get our hands dirty with a little bit for coding as well. Objectives of this article: Discuss Data types, built-in, and derived data … Read more

Why SME’s must approach analytics differently to large enterprises

Many people during lockdown have taken to learning new skills, and a popular one is data science. The only problem is that often these are courses based on methods used by big companies and thus aren’t practical for SME’s (Small to medium-sized businesses). The Reason: Extrapolation Okay, why? Picture this, there is a 5kg bag … Read more

Web Scraping with rvest: Exploring Sports Industry Jobs

Web scraping with rvest is easy and, surprisingly, comes in handy in situations that you may not have thought of. For example, one of the unique things about academics is the constant need to stay “ahead of the curve,” meaning being nimble enough as a program to shift curriculum around to provide students training and … Read more

Categories R Tags ExcerptFavorite

Taking care of business with Responsible AITaking care of business with Responsible AIDirector, Product Strategy & Operations, Cloud AI

In less than 10 years, some predict that Artificial Intelligence (AI) may be the #1 driver of global GDP growth1. This is a staggering prediction. Over this next decade, we will see incredible adoption and innovation; in fact, applications that aren’t AI-enabled may feel broken. Despite this excitement, I have seen first-hand that trust in … Read more

Why R? Webinar – Reproducible research with workflowr

[This article was first published on http://r-addict.com, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. Why R? Webinars are back for Season 2! After over more than 20 … Read more

Categories R Tags ExcerptFavorite

5 ways to optimize your backup costs with Azure Backup

Achieving cost efficiency in your cloud usage is more critical today than ever before. At Azure Backup, we’re committed to helping you optimize your backup costs. Over the last few months, we’ve introduced a comprehensive collection of features that not only gives you more visibility into your backup usage, but also helps you take action … Read more

September 2020 ISC Call for Proposals – Now Open!

[This article was first published on R Consortium, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. The deadline for submitting proposals is midnight, October 1st, 2020. The September … Read more

Categories R Tags ExcerptFavorite

10 Guidelines to Better Table Design

[This article was first published on r – paulvanderlaken.com, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. ShareTweet Jon Schwabisch recently proposed ten guidelines for better table design. … Read more

Categories R Tags ExcerptFavorite

How To Host Your Own Python Models

The first thing you’re going to need to do in order to serve any sort of files to the world wide web is set up port forwarding. Port forwarding allows your local connection to your internet service provider and network to be not only incoming from networks, but also outgoing into networks. Web-pages and websites … Read more

What XGBoost is and how to optimize it

In the world of machine learning and Kaggle competitions, the XGBoost algorithm has the first place. Introduction Like many data scientists, XGBoost is now part of my toolkit. This algorithm is among the most popular in the world of data science (real-world or competition). Its multitasking aspect allows it to be used in regression or … Read more

3 Deep Learning Algorithms in under 5 minutes — Part 2 (Deep Sequential Models)

In the last article, we looked at models that deal with non-time-series data. Time to turn our heads towards some other models. Here we will be discussing deep sequential models. They are predominantly used to process/predict time series data. Link to Part 1, in case you missed it. Simple recurrent neural networks (referred to also … Read more

Updating a Quip Spreadsheet with Python API

What is Quip and Why Should You Care? Quip is a collaborative productivity software suite for mobile and the Web. It allows groups of people to create and edit documents and spreadsheets as a group, typically for business purposes. (Wikipedia) A major difference between Quip and Google Docs/Sheets is that Quip has a native desktop … Read more

5 Free and Fun APIs to Use For Learning, Personal Projects, and More!

You’ll be pleasantly surprised by what’s out there. Art by siscadraws Public APIs are awesome! There are over 50 pieces covering APIs on just the Towards Data Science publication, so I won’t go into too lengthy of an introduction. APIs basically let you interact with some tool or service (which could be provided by literally … Read more

NLP: preparing data

[This article was first published on Rbloggers – The Analytics Lab, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here) Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t. Favorite

Categories R Tags ExcerptFavorite

Amazon CloudFront announces real-time logs

CloudFront has supported delivery of access logs to customer’s Amazon S3 buckets and the logs are typically delivered in a matter of minutes. However, some customers have time sensitive use cases and require access log data quickly. With the new real-time logs, data is available to you in a matter of a few seconds with … Read more

Categories AWS ExcerptFavorite