artificialintelligence

April 27, 2020

Modeling Bank’s Churn Rate with AdaNet: A Scalable, Flexible Auto-Ensemble Learning Framework

Logistic Regression with Google’s AdaNet- Auto Learning Ensemble Framework Motivation AdaNet provides a framework that could automatically produce a high-quality model given an arbitrary set of features and a model search space. In addition, it builds ensembles from productionized TensorFlow models to: Reduce churn, reuse domain knowledge, and conform with business and explainability requirements. The framework is capable of handling datasets containing thousands to billions of examples, in a distributed environment. Several open-source AutoML frameworks, […]

Read More+

Blockdrop to Accelerate Neural Network training

AI Research

April 26, 2020

Blockdrop to Accelerate Neural Network training by IBM Research

Scaling AI with Dynamic Inference Paths in Neural Networks Introduction IBM Research, with the help of the University of Texas Austin and the University of Maryland, has tried to expedite the performance of neural networks by creating a technology, called BlockDrop. Behind the design of this technology lies the objective and promise of speeding up convolutional neural network operations without any loss of fidelity, which can offer a great savings of cost to the ML […]

Read More+

Deep Learning, Matrix Factorization, Traditional Machine Learning

April 26, 2020

Profiling Matrix Factorization and Recommendation Engines with Python

Profiling Statistics of Python Libraries and Insights of New/Emerging Factorization Techniques Introduction In my previous blog, I narrated about different matrix factorization techniques, citing pros and cons of each of the libraries. In this blog, I will give some code samples of some of the previously discussed libraries. We will also see the profiling statistics of some of the python libraries (for SVD/Recommendation Engine) so as to understand the time taken to execute the training engine, […]

Read More+

Different types of Matrix Factorization Techniques and Scaling mechanisms for online Recommendation Engines

Data Science Basics, Deep Learning, Matrix Factorization

April 26, 2020

Overview of Matrix Factorization Techniques using Python

Different types of Matrix Factorization Techniques and Scaling mechanisms for online Recommendation Engines Introduction Low-rank approximations of data matrices have become an important tool in Machine Learning in the field of bio-informatics, computer vision, text processing, recommender systems, and others. They provide efficient compact representation of multi-dimensional vectors by embedding high dimensional data in lower dimensional spaces. In such representations, it comes to rescue by mitigating noise, unfolding latent relations, and facilitates further processing. In […]

Read More+

AI Research

April 26, 2020

Torchmeta: A Meta-learning library for PyTorch

Introduction Meta-learning research and open source libraries have offered a way to get a detailed comparison between different algorithms. It offers standardized benchmarks and a wide range of datasets available allowing full control over the complexity of algorithm training and testing,However, most of the code available online suffers from the following limitations: The data pipeline built in traditional and conventional production systems relies on training dataset when the model is first built. The model is […]

Read More+