Solve real-world problems using Deep Learning & Artificial Intelligence

Every new technology introduced has had a purpose(almost always). Usually, it is a solution to a certain problem(s) identified by its creator while brainstorming. But when we talk about Artificial Intelligence, which is a largely unexplored yet constantly evolving field of computing, we often get detracted by the spruced-up object detection projects.

Read More

Deep Learning is already dead: Towards Artificial Life with Olaf Witkowski

In his own words, Witkowski says, “artificial intelligence means that you are trying to copy human intelligence as best as possible. Artificial life says, okay, that’s good, but let’s try to understand human intelligence and recreate it from the fundamental knowledge we have acquired. It’s more constructive. It’s a bit like the Richard Feynman quote: what I cannot create, I do not understand.”

Read More

Neural Hallucinations

When a human sees an object, certain neurons in our brain’s visual cortex light up with activity, with hallucinogenic drugs our serotonin receptors overwhelm and lead to the distorted perception. Similarly, deep neural networks that are modelled on structures in our brain… when these neural network’s activation is overstimulated (virtual drugs), we get phenomenons like neural dreams and neural hallucinations.

Read More

5 essential product classification papers for Data Scientists

@LimarcLimarc Ambalina

Editor @Hackernoon by day, VR Gamer and Anime Binger by night

Product categorization/product classification is the organization of products into their respective departments or categories. As well, a large part of the process is the design of the product taxonomy as a whole.

Product categorization was initially a text classification task that analyzed the product’s title to choose the appropriate category. However, numerous methods have been developed which take into account the product title, description, images, and other available metadata.

The following papers on product categorization represent essential reading in the field and offer novel approaches to product classification tasks.

1. Don’t Classify, Translate
In this paper, researchers from the National University of Singapore and the Rakuten Institute of Technology propose and explain a novel machine translation approach to product categorization. The experiment uses the Rakuten Data Challenge and Rakuten Ichiba datasets. Their method translates or converts a product’s description into a sequence of tokens which represent a root-to-leaf path to the correct category. Using this method, they are also able to propose meaningful new paths in the taxonomy.

The researchers state that their method outperforms many of the existing classification algorithms commonly used in machine learning today.

Published/Last Updated – Dec. 14, 2018

Authors and Contributors – Maggie Yundi Li (National University of Singapore), Stanley Kok (National University of Singapore), and Liling Tan (Rakuten Institute of Technology)

[Read Now]

2. Large-Scale Categorization of Japanese Product Titles Using Neural Attention Models
The authors of this paper propose attention convolutional neural network (ACNN) models over baseline convolutional neural network (CNN) models and gradient boosted tree (GBT) classifiers. The study uses Japanese product titles taken from Rakuten Ichiba as training data. Using this data, the authors compare the performance of the three methods (ACNN, CNN, and GBT) for large-scale product categorization. While differences in accuracy can be less than 5%, even minor improvements in accuracy can result in millions of additional correct categorizations. 

Lastly, the authors explain how an ensemble of ACNN and GBT models can further minimize false categorizations.

Published/Last Updated – April, 2017 for EACL 2017

Authors and Contributors – From the Rakuten Institute of Technology: Yandi Xia, Aaron Levine, Pradipto Das Giuseppe Di Fabbrizio, Keiji Shinzato and Ankur Datta 

[Read Now]

3. Atlas: A Dataset and Benchmark for Ecommerce Clothing Product Classification

Image via

Researchers at the University of Colorado and Ericsson Research (Chennai, India) have created a large product dataset known as Atlas. In this paper, the team presents their dataset which includes over 186,000 images of clothing products along with their product titles.

Furthermore, they introduce related work in the field that has influenced their study. Finally, they test their dataset using a Resnet34 classification model and a Seq to Seq model to categorize the products. The data is taken from Indian ecommerce stores, so some of the categories used may not be applicable to Western markets. However, the dataset has been open-sourced and is available on Github. 

Published/Last Updated – Aug. 19, 2019

Authors and Contributors – Venkatesh Umaashankar (Ericsson Research),  Girish Shanmugam (Ericsson Research), and Aditi Prakash (University of Colorado)

[Read Now]

4. Large Scale Product Categorization using Structured and Unstructured Attributes
In this study, a team at WalmartLabs compares hierarchical models to flat models for product categorization.

The researchers employ deep-learning based models which extract features from each product to create a product signature. In the paper, the researchers describe a multi-LSTM and multi-CNN based approach to this extreme classification task. Furthermore, they present a novel way to use structured attributes. The team states that their methods can be scaled to take into account any number of product attributes during categorization. 

Published/Last Updated – Mar. 1, 2019

Authors and Contributors – From WalmartLabs: Abhinandan Krishnan and Abilash Amarthaluri

[Read Now]

5. Multi-Label Product Categorization Using Multi-Modal Fusion Models
In this paper, researchers from New York University and U.S. Bank investigate multi-modal approaches to categorize products on Amazon. Their approach utilizes multiple classifiers trained on each type of input data from the product listings. Using a dataset of 9.4 million Amazon products, they developed a tri-modal model for product classification based on product images, titles, and descriptions. Their tri-modal late fusion model retains an F1 score of 88.2%. 

The findings of their study demonstrate that increasing the number of modalities could improve performance in multi-label product categorization.

Published/Last Updated – June 30, 2019

Authors and Contributors – Pasawee Wirojwatanakul (New York University) and Artit Wangperawong (U.S. Bank)

[Read Now]

In the papers on product categorization above, the researchers trained their models on open datasets which included millions of products. However, if you are building a product categorization model for commercial use, these datasets will not be available to you. 

Take a look at Kaggle, Google Dataset Search, and the Ultimate Dataset Library, for open data that may be of use to you.

Also published at

Share this story


pre-emoji story

pre-emoji story


Subscribe to get your daily round-up of top tech stories!

Read More

The last Machine & Deep-Learning Compendium you’ll ever need

In the last 3 years, I have been curating everything related, directly or indirectly, to machine-learning (ML), deep-learning (DL), Statistics, Probability, NLP, NLU, deep-vision, etc. I started curating a compendium because I wanted to expand the scope of my knowledge. I believe that every researcher and data scientist (DS) should strive to learn more on a daily basis, not by hitting task-related walls and solving them, but as a lifelong learning practice.

Read More

Continual learning — where are we?

“Continuous learning ability is one of the hallmarks of human intelligence.” — Lifelong Machine Learning. As the deep learning community aims to bridge the gap between human and machine intelligence, the need for agents that can adapt to continuously evolving environments is growing more than ever.

Read More

Solution to value aggregation

Solution Value Aggregation

AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of challenges including personal value extraction, multi-agent value merger and finally in-silico encoding. State-of-the-art research in value alignment shows…

Read More

From von Neumann to Memory-Augmented Neural Networks

The traditional von Neumann architecture differentiates between a CPU (Central Processing Unit) and three levels of memory: registers — very fast, but with storage capability limited to a few values; main memory (e.g. RAM)— faster, with enough storage to accommodate for instructions and data to run a program, and external memory (e.g. hard drive) — slow, but with room for virtually all data used by a computer.

Read More

Why Deep Learning is still too difficult

Deep Learning is still too difficult

While deep learning has great potential, building practical applications powered by deep learning remains to be too expensive and too difficult for many organizations. In this article, we will describe some of the challenges to broader adoption of deep learning.

Read More

Two tools every Data Scientist should use for their next ML project

For my project, I am creating an Ensemble. An Ensemble is a collection of machine learning algorithms that each individually train and predict on the same data. The advantage of an Ensemble is that it provides a range of different strategies for finding a solution and utilizes a majority vote that democratizes the classification by all the models.

Read More
1 2 3 5