A detailed walkthrough of preprocessing a sample corpus with the NLTK library using stemming and lemmatization. Read More
Monthly Archives: December 2020
Learn NLP the Stanford Way — Lesson 2
Second in an n-part series. Deep dive into Word2vec, GloVe, and word senses. Read More
Learn NLP the Stanford way — Lesson 1
The AI area of Natural Language Processing, or NLP, throughout its gigantic language models — yes, GPT-3, I’m watching you — presents what it’s perceived as a revolution in machines’ capabilities to perform the most distinct language tasks.
Due to that, the perception of the public as a whole is split: some perceive that these new language models are going to pave the way to a Skynet type of technology, while others dismiss them as hype-fueled technologies that will live in dusty shelves, or HDD drives, in little to no time.
Motivated by this, this series of storiesapproaches NLP from scratch in a friendly way. Read More
AutoX becomes China’s first to remove safety drivers from robotaxis
Residents of Shenzhen will see truly driverless cars on the road starting Thursday. AutoX, a four-year-old startup backed by Alibaba, MediaTek and Shanghai Motors, is deploying a fleet of 25 unmanned vehicles in downtown Shenzhen, marking the first time any autonomous driving car in China tests on public roads without safety drivers or remote operators.
The cars, meant as robotaxis, are not yet open to the public, an AutoX spokesperson told TechCrunch. Read More
Noam Chomsky on the Future of Deep Learning
For the past few weeks, I’ve been engaged in an email exchange with my favourite anarcho-syndicalist Noam Chomsky. I reached out to him initially to ask whether recent developments in ANNs (artificial neural networks) had caused him to reconsider his famous linguistic theory Universal Grammar. Our conversation touched on the possible limitations of Deep Learning, how well ANNs really model biological brains and also meandered into more philosophical territory. I’m not going to quote Professor Chomsky directly in this article as our discussion was informal but I will attempt to summarise the key take-aways. Read More
Model describes complete grasping movement planning in the brain
Neuroscientists at the German Primate Center (DPZ)-Leibniz Institute for Primate Research in Göttingen have developed a model that can seamlessly represent the entire planning of movement from seeing an object to grasping it. Comprehensive neural and motor data from grasping experiments with two rhesus monkeys provided decisive results for the development of the model, an artificial neural network that is able to simulate processes and interactions in the brain after training with images of specific objects. The neuronal data from the artificial network model were able to explain the complex biological data from the animal experiments and thus prove the validity of the functional model. This could be used in the long term for the development of better neuroprostheses, for example, to bridge the damaged nerve connection between brain and extremities in paraplegia and thus restore the transmission of movement commands from the brain to arms and legs. Read More
Use real-time anomaly detection reference patterns to combat fraud
Businesses of every size and shape have a need to better understand their customers, their systems, and the impact of external factors on their business. How rapidly businesses mitigate risks and capitalize on opportunities can set apart successful businesses from businesses that can’t keep up. Anomaly detection—or in broader terms, outlier detection—allows businesses to identify and take action on changing user needs, detect and mitigate malignant actors and behaviors, and take preventive actions to reduce costly repairs.
The speed at which businesses identify anomalies can have a big impact on response times, and in turn, associated costs.
… At Google Cloud, our customer success teams have been working with an increasing number of customers to help them implement streaming anomaly detection. In working with such organizations to help them build anomaly detection systems, we realized that providing these reference patterns can significantly reduce the time to solution for those and future customers. Read More
Police Drones Are Starting to Think for Themselves
When the Chula Vista police receive a 911 call, they can dispatch a flying drone with the press of a button. …Each day, the Chula Vista police respond to as many as 15 emergency calls with a drone, launching more than 4,100 flights since the program began two years ago. …The latest drone technology — mirroring technology that powers self-driving cars — has the power to transform everyday policing, just as it can transform package delivery, building inspections and military reconnaissance. Rather than spending tens of millions of dollars on large helicopters and pilots, even small police forces could operate tiny autonomous drones for a relative pittance. Read More
Using an AI COE (Center of Excellence) to Bridge from Experimentation to Mastery
Summary: There is now sufficient experience among mid and large sized companies starting their AI journey to identify a single best practice for moving from AI experimentation to scale-up: the AI COE (Center of Excellence).
If you are a mid-sized business, government organization, or educational institution chances are pretty much 100% that you already have AI somewhere in your company.
AI is embedded in so many modern applications that some version of NLP, machine vision, text recognition, or a recommender or behavioral predictor of some sort is already hard at work without you’re really having to do much beyond the original customization and implementation. Read More
Neuroscientists find a way to make object-recognition models perform better
Computer vision models known as convolutional neural networks can be trained to recognize objects nearly as accurately as humans do. However, these models have one significant flaw: Very small changes to an image, which would be nearly imperceptible to a human viewer, can trick them into making egregious errors such as classifying a cat as a tree.
A team of neuroscientists from MIT, Harvard University, and IBM have developed a way to alleviate this vulnerability, by adding to these models a new layer that is designed to mimic the earliest stage of the brain’s visual processing system. In a new study, they showed that this layer greatly improved the models’ robustness against this type of mistake. Read More
Rick's Cafe AI 