notes  in  machine

yesterday at 10:48PM  by:shuri
Viewable by:

source The Brain ‘Rotates’ Memories to Save Them From New Sensations
Some populations of neurons simultaneously process sensations and memories. New work shows how the brain rotates those representations to prevent interference.
Thursday, April 08, 07:54PM  by:shuri
Viewable by:

source Neuralink
Developing ultra high bandwidth brain-machine interfaces to connect humans and computers.
Wednesday, April 07, 12:39PM  by:shuri
Viewable by:

source Are Deep Neural Networks Dramatically Overfitted?
If you are, like me, confused by why deep neural networks can generalize to out-of-sample data points without drastic overfitting, keep on reading.
Wednesday, April 07, 12:38PM  by:shuri
biology of memory,
engram cells,
memory formation,
synaptic plasticity,
li-huei tsai,
marco asaf,
Viewable by:

source Neuroscientists discover a molecular mechanism that allows memories to form
Encoding memories in engram cells is controlled by large-scale remodeling of the proteins and DNA that make up cells’ chromatin, according to an MIT study. This chromatin remodeling, which allows specific genes involved in storing memories to become more active, takes place in multiple stages spread out over several days.
Tuesday, March 23, 11:43AM  by:shuri
Viewable by:

source Matrix Multiplication Inches Closer to Mythic Goal
A recent paper set the fastest record for multiplying two matrices. But it also marks the end of the line for a method researchers have relied on for decades to make improvements.
Saturday, March 06, 09:51AM  by:shuri
Viewable by:

source Facial recognition technology can expose political orientation from naturalistic facial images
Ubiquitous facial recognition technology can expose individuals’ political orientation, as faces of liberals and conservatives consistently differ. A facial recognition algorithm was applied to naturalistic images of 1,085,795 individuals to predict their political orientation by comparing their similarity to faces of liberal and conservative others. Political orientation was correctly classified in 72% of liberal–conservative face pairs, remarkably better than chance (50%), human accuracy (55%), or one afforded by a 100-item personality questionnaire (66%). Accuracy was similar across countries (the U.S., Canada, and the UK), environments (Facebook and dating websites), and when comparing faces across samples. Accuracy remained high (69%) even when controlling for age, gender, and ethnicity. Given the widespread use of facial recognition, our findings have critical implications for the protection of privacy and civil liberties.
Thursday, March 04, 07:02PM  by:shuri
Viewable by:

source Visualizing Hierarchical Models
A visual explanation of multi-level modeling
Saturday, February 20, 11:31AM  by:shuri
Viewable by:

source The Shoddy Science Behind Emotional Recognition Tech | by Dave Gershgorn | Feb, 2021 | OneZero
OneZero’s General Intelligence is a roundup of the most important artificial intelligence and facial recognition news of the week. Facial recognition isn’t just for verifying a person’s identity. In…
Thursday, February 18, 03:51PM  by:shuri
artificial intelligence,
deep learning,
machine learning,
neural networks,
natural language processing,
ml & data engineering,
google trillion parameter ai,
Viewable by:

source Google Open-Sources Trillion-Parameter AI Language Model Switch Transformer
Researchers at Google Brain have open-sourced the Switch Transformer, a natural-language processing (NLP) AI model. The model scales up to 1.6T parameters and improves training time up to 7x compared
Tuesday, February 09, 11:55AM  by:shuri
Viewable by:

source This is how we lost control of our faces
The largest ever study of facial-recognition data shows how much the rise of deep learning has fueled a loss of privacy.
Friday, February 05, 12:14PM  by:shuri
Viewable by:

source Deep learning doesn’t need to be a black box - KDnuggets
The cultural perception of AI is often suspect because of the described challenges in knowing why a deep neural network makes its predictions. So, researchers try to crack open this "black box" after a network is trained to correlate results with inputs. But, what if the goal of explainability could…
Friday, January 29, 09:31PM  by:shuri
identity management,
novel coronavirus,
Viewable by:

source Onfido, the AI-based ID verification platform, raises $100M led by TPG – TechCrunch
Contactless transactions have become a major priority at a time when people all around the world are minimising their contact with others outside their households to slow down the often-insidious spread of the novel coronavirus. But if a lot of the consumer focus lately has been on things like payments or deliveries, that’s overlooking the fact […]
Tuesday, January 26, 05:39PM  by:shuri
claude shannon,
at&t archives,
in their own words,
Viewable by:

source AT&T Archives: Claude Shannon Demonstrates Machine Learning
Claude Shannon demonstrates machine learning using electromagnets, relay circuits, and a magnetic mouse named
Sunday, January 24, 04:24PM  by:shuri
voice assistant,
amazon alexa,
conversational ai,
fiat chrysler,
Viewable by:

source Amazon Debuts ‘Alexa Custom Assistant’ for Building Branded Voice Assistants Starting With Fiat Chrysler
Alexa Custom Assistant is Amazon’s new conversational AI platform companies can use to build branded virtual assistants supported by Alexa..
Monday, January 11, 11:32AM  by:shuri
Viewable by:
Monday, January 11, 11:30AM  by:shuri
Viewable by:

source 70TB of Parler users’ data leaked by security researchers | CyberNews
Parler has been hit by a massive data scrape. Security researchers collected swaths of user data before the network went dark Monday morning.
Wednesday, January 06, 10:59AM  by:shuri
Viewable by:

source 15.ai: Natural TTS with minimal data
15.ai: Natural high-quality faster-than-real-time text-to-speech synthesis with minimal data