Ask Slater Machine Learning What is a tensor in physics terminology and what’s the difference from a tensor in machine learning and AI? June 24, 2019 by adamdev Thereās no difference. A tensor is just a very, very generic term for: basically anything. A tensor is a generic term for a way of arranging numbers that generally has some geometric interpretation. A scalar (math speak for a number) is a 0-tensor. A vector (math speak for a list of numbers) is a 1-tensor […] Read more Ā»
Ask Slater Machine Learning How does the ELMo machine learning model work? June 12, 2019 by adamdev At its core, ELMo is an RNN model with an LSTM gating setup thatās trained as a bidirectional language model. But thatās not really what you asked. You asked how it works. Itās often really tough to explain how a machine learning model works. Importantly you have to understand that no part of what I […] Read more Ā»
Ask Slater Machine Learning Should we remove duplicates from a data-set while training a Machine Learning algorithm (shallow and/or deep methods)? February 6, 2019 by adamdev Itā¦depends. Mostly it depends on what your goals are and what your dataset looks like. There are two big divides here on both sides. Data Structured Data – here, duplicates very much come with the territory. In this situation youāve also likely got a lot of implicit ambiguity in your problem. Letās say that you […] Read more Ā»
Business Machine Learning Opinion Piece 5 Predictions for AI & Intelligent Process Automation in 2019 December 21, 2018 by adamdev As we close out 2018 here are 5 predictions on where AI is headedĀ in the new year. #1: AI/Data Science Meets the Line of Business One of AIās biggest obstacles has been the disconnect between data science teams and subject matter experts (SMEs) in the business. SMEs play a critical role but the complexity of […] Read more Ā»
Machine Learning Text Data Use Case Tutorials Small Data for Big Problems: Practical Transfer Learning for NLP October 11, 2018 by adamdev Yesterday, Indicoās CTO Slater Victoroff held a webinar to discusses modern transfer learning techniques for NLP to help you avoid common pitfalls when working in low-data environments. If you missed it, the slides and video are now available below. Overview Despite all the advancements using AI and machine learning to create value around structured data, […] Read more Ā»
Data Science Developers Machine Learning Text Data Use Case Tutorials Model Finetuning for Fun and Profit September 18, 2018 / October 9, 2025 by adamdev In our last blog post, “Effective Transfer Learning for NLP” we walked through the technological advancements that have made model finetuning practical for natural language processing. In this post, we’ll dive into the details and take a look at how you can start using Indico’s python library, finetune, to try out model finetuning on your […] Read more Ā»
Machine Learning More Effective Transfer Learning for NLP August 22, 2018 / October 9, 2025 by adamdev This spring I presented a talk entitled “Effective Transfer Learning for NLP” at ODSC East. The talk was intended to demonstrate how surprisingly effective pre-trained word and document embeddings are at low training data volumes, and to lay out a set of practical recommendations for applying these techniques to your own tasks. Thanks to some […] Read more Ā»
Data Science Machine Learning Text Data Use Case ODSC 2018: Effective Transfer Learning for NLP July 5, 2018 by adamdev Our machine learning architect and co-founder, Madison May, was a featured presenter at the 2018 Open Data Science Conference (ODSC). His technical talk focused on transfer learning, how it can be used to deliver efficiencies in machine learning on text-based content and how Indico has incorporatedĀ transfer learning into our commercial Intelligent Process Automation software. If […] Read more Ā»
Announcements Data Science Indico Machine Learning Enso: An Open Source Library for Benchmarking Embeddings + Transfer Learning Methods June 26, 2018 by adamdev Because Indico has benefited so much from hard work in the open-source community, we like to make sure a portion of our time is spent giving back. As part of this initiative, we’re releasing Enso, an open-source python library for benchmarking document embeddings and transfer learning methods. Enso was created in part to help measure […] Read more Ā»
Data Science Machine Learning Everything You Wanted to Know About Optimization May 17, 2018 by adamdev Last week our co-founder and machine learning architect, Madison May, presented at the Boston Machine Learning Meetup on various optimization methods based on trends from ICLR 2018. Video and slides below. Ā Ā Overview In recent years the use of adaptive momentum methods like Adam and RMSProp has become popular in reducing the sensitivity of […] Read more Ā»
