In this series of blog posts we’re taking a deep dive into the new on-device model personalization features from Core ML 3. I’ll show how to create a customizable image classifier using k-Nearest Neighbors as well as a deep neural network, right from inside an iOS app. This is part 2 of a four-part series: Introduction to on-device training Rock, Paper, Scissors (Lizard? Spo
An experiment showing adversarial robustness makes neural style transfer work on a non-VGG architecture
Section 3.2 of Ilyas et al. (2019) shows that training a model on only adversarial errors leads to non-trivial generalization on the original test set. We show that these experiments are a specific case of learning from errors.
This workshop is sold out! Provalis Research is holding a three-day training workshop for QDA Miner 5 and WordStat 8 in San Diego, CA. The training will be held from December 16 to December 18, 2019 (from 9:00 am to 5:00 pm), at University of California San Diego. Click here for a detailed description of the workshop. Each […]
The recent advances in deep learning have done more than just make money for startups and tech companies. They've also infiltrated neuroscience! Deep neural networks---models originally inspired by the basics of the nervous system---are finding ever more applications in the quest to understand the brain. We talk about many of those uses in the episode. After first describing more traditional approaches to modeling behavior, we talk about how neuroscientists compare deep net models to real brains
CLARIN ERIC is a research infrastructure through Europe and beyond to encourage the sharing and sustainability of language data and tools for research in the humanities and social sciences. We are pleased to announce that our functions for text analysis in Google Sheets were featured in the July 2019 issue of the CLARIN Newsflash. We are still wor
Spreadsheets are an increasingly popular way of storing all kinds of information, including text, and giving it some informal structure, and systems like Google Sheets are especially popular for collaborative work and sharing data. In response to the demand for standard natural language processing (NLP) tasks in spreadsheets, we have developed a Google Sheets add-on that provides functions to carry out the following tasks on text cells using GATE Cloud services: named
Restricted learning and intrinsic plasticity explained
In collaboration with Headstart (a charitable trust that provides hands-on science, engineering and maths taster courses), the Department of Computer Science has just run its fourth annual summer school for maths and science A-level students. This residential course ran from 8 to 12 July 2019 and included practical work in computer programming, Lego robots, and project development as well as tours of the campus and talks about the industry. For the third year in a row, we hav
This is a psuedo-transcript for a talk given at Deconstruct 2019. To make this accessible for people on slow connections as well as people using screen readers, the slides have been replaced by in-line text (the talk has ~120 slides; at an average of 20 kB per slide, that's 2.4 MB. If you think that's trivial, consider that <a href="https://blogs.microsoft.com/on-the-issues/2019/04/08/its-time-for-a-new-approach-for-mapping-broadband-data-to-be
JAX is a great linear algebra + automatic differentiation library for fast experimentation with and teaching machine learning. Here is a lightweight example, in just 75 lines of JAX, of how to implement Real-NVP . This post is based off of a tutorial on normalizing flows I gave at the ICML workshop on <a href="htt
This is a tutorial on common practices in training generative models that optimize likelihood directly, such as autoregressive models and normalizing flows . Deep generative modeling is a fast-moving field, so I hope for this to be a newcomer-friendly introduction to the basic evaluation terminology used consistently across r
12th GATE Training Course: open-source natural language processing with an emphasis on social media For over a decade, the GATE team has provided an annual course in using our technology. The course content and track options have changed a bit over the years, but it always includes material to help novices get started with GATE as well as introductory and more advanced use of the JAPE language for matching pattern
Monitoring Implementation of CRPD and SDG Through Big Data Analytics and Text Mining Derrick L. Cogburn American University Introduction As we look at the major global frameworks to support disability-inclusive international development, especially the 2030 Sustainable Development Goals, the United Nations Convention on the Rights of Persons with Disabilities (CRPD), the Habitat III […]
In May 2019 we submitted a prototype to the United Nations General Assembly Resolutions Extraction and Elicitation Global Challenge , which asked for submissions using mature natural language processing techniques to produce semantically enhanced, machine-readable documents from PDFs of UN GA resolutions, with particular interest in identifying named entities and items in certain thesauri and ontologies
From worms to flies, and mice to macaques, neuroscientists study a range (but not very large range...) of animals when they study "the brain". On this episode we ask a lot of questions about these model organisms, such as: how are they chosen? should we use more diverse ones? and what is a model organism actually a model of? We also talk about how the development of genetic tools for certain animals, like mice, have made them the dominant lab animal and the difficulty of bringing a new model spe
the number of modules (cortical microcolumns) increased
What is Observational Research? Watch what I do, not what I say, could be a good lead-in for Observational Research. People in focus groups or in surveys may say one thing such as, “I always buy green apples” but perhaps when observed they buy the less costly apples, or the freshest looking apples. Observational research […]
As you may have seen in the WWDC 2019 videos , Core ML 3 adds a lot of new stuff to machine learning on iOS. The new killer feature is on-device training of models, but it can now also run many advanced model architectures — and thanks to the addition of many new layer types, it should even be able to run new architectures that haven’t been invented yet! <a href="https://developer.ap
“soft-coded” (dopamine-coded) synapses depend on dopamine levels and are realized by presynaptic/postsynaptic dopamine receptors.
The Brexit Party attracted the most engagement on Twitter in the run-up to the UK European Parliament election on May
Our distributor in Australia, SurveyDesign.com has written this quick Blog that we thought you might find instructive: How to Import PDF’s into WordStat for Stata. You can also see a video tutorial on our website on how to import PDF and other documents such as ASCII, Rich Text Format, MS Word, HTML and WordPerfect documents […]
Working memory is the ability to keep something in mind several seconds after it's gone. Neurons don't tend to keep firing when their input is removed, so how does the brain hold on to information when it's out of sight? Scientists have been probing this question for decades. On this episode, we talk about how working memory is studied and the traditional view of how it works, which includes elevated persistent firing rates in neurons in the prefrontal cortex. The traditional view, however, is b
Translations: 中文 I've been at Google Brain robotics (now referred to as Robotics @ Google ) for nearly 3 years. It's helpful to reflect, from time to time, on the scientific, engineering and personal productivity takeaways gleaned from working on large research projects. Every res
Snapchat's new gender-bending filter is a source of endless fun and laughs at parties. The results are very pleasing to look at. As someone who is used to working with machine learning algorithms, it's almost magical how robust this feature is. I was so duly impressed that I signed up for Snapchat and fiddled around with it this morning to try and figure out what's going on under the hood and how I might break it. N.B, this is not a s
GATE at World Press freedom day: STRENGTHENING THE MONITORING OF SDG 16.10.1 <div
Social media platforms are becoming ubiquitous in the tourism industry around the world. Travelers are using social media to write reviews, plan travel, connect with others and communicate with providers. Likewise, airlines, hotels, restaurants and tour companies, are using social media to market and promote their products, communicate with their clients and as […]
In 2002, cancer biologist Yuri Lazebnik raised and addressed the semi-facetious question "Can a biologist fix a radio?" in a short paper. The paper is a critique of current practices in the biological sciences, claiming they are inefficient at getting to truth. We discuss the stages of research progress in biological science Yuri describes, including the "paradoxical" stage where more facts leads to less understanding. We then dive into his view of how a biologist would approach a radio: describ
Announcing WeVerify: a new project developing AI-based tools for computer-supported digital content verification. The WeVerify platform will provide an independent and community driven environment for the verification of online content, to be used to assist journalists in gathering and verifying quickly online content. Prof. Kalina Bontcheva will be serving as the Scientific Director of the project. Onl
What we'd like to find out about GANs that we don't know yet.
Next.js 8.0.4 introduces build performance improvements, smaller bundles, stonger defaults, and more.
Despite the fact that the brain is full of them, glial cells don't get much attention from neuroscientists. The traditional view of these non-neurons is that they are supportive cells---there to silently help neurons do what they need to do. On this episode we start by describing this traditional view, including types of glial cells and their roles. Then we get into the more interesting stuff. How do glia communicate with each other and with neurons? Turns out there are many chemical messages th
We’re looking for a new CEO for Stack Overflow. I’m stepping out of the day-to-day and up to the role of Chairman of the Board. Read more "The next CEO of Stack Overflow"
INTRODUCTION Part I of our blog series introduced Automatic Machine Learning Document Classification (AML-DC). Part II of our blog series on Automatic Machine Learning Document Classification (AML-DC) provides a practical and detailed walkthrough on the development and implementation of a supervised AML-DC model in fast, reproducible, reliable and auditable way. RESEARCH PROBLEM How does one […]
Provalis Research is holding a three-day training workshop on QDA Miner 5 and WordStat 8 in Montreal, Canada. The training will be held from May 29 to 31, 2019, at Provalis Research head office. Click here for a detailed description of the workshop. Each participant is required to bring his/her own laptop computer. The early pre-registration price for 3-day […]
It is approaching that time of the year again! The GATE training course will be held from 17-21 June 2019 at the University of Sheffield, U
Xiaoyi Yin has graciously translated this blog post to 中文 . I often hear the remark around the proverbial AI watering hole that there are no examples of reinforcement learning (RL) deployed in commercial settings that couldn’t be replaced by simpler algorithms. This is somewhat true. If one takes RL to mean “ne
Provalis Research is holding a three-day training workshop for QDA Miner 5 and WordStat 8 in Madrid, Spain. The training will be in English and will held from June 3 to 5, 2019, at Universidad de Navarra : Marquesado de Santa Marta, 3, Madrid. Click here for a detailed description of the workshop. Each participant is required to bring his/her […]
GATE Cloud is GATE, the world-leading text-analytics platform, made available on the web with both human user interfaces and programmatic ones. My name is David Jones and part of my role is to make it easier for you to use GATE. This article is aimed at Python programmers and people who are, rightly, curious to see if Python can help with their text analysis work. GATE Cloud exposes a web API for many of its services. In this arti
Referendum result Although the UK voted by a narrow margin in the UK EU membership referendum in 2
