ArtificialIntelligenceArticles
3.03K subscribers
1.64K photos
9 videos
5 files
3.86K links
for who have a passion for -
1. #ArtificialIntelligence
2. Machine Learning
3. Deep Learning
4. #DataScience
5. #Neuroscience

6. #ResearchPapers

7. Related Courses and Ebooks
Download Telegram
Towards Open-Set Semantic Segmentation of Aerial Images. http://arxiv.org/abs/2001.10063
i. Build knowledge of ML, read textbooks, theses & papers,
ii. Read a lot of papers, & assess them critically,
iii. Read PhD theses of researchers whose work interests you,
iv. Reimplement alg's from these source(s),
v. Read & skim papers with a critical eye,
vi. Notice trends
The Case for Bayesian Deep Learning
Andrew Gordon Wilson: https://arxiv.org/abs/2001.10995
#Bayesian #DeepLearning #MachineLearning
ArtificialIntelligenceArticles
I've launched a project, concerning construction of an ai based nCov coronavirus detector. All data scientists/machine learning developers/ai devs are welcome to contribute, or point to similar projects. https://github.com/JordanMicahBennett/SMART-CORONA…
new update :

1) With the goal of getting as close to real time in detection as possible, I've found out about MinION dna sequencer device, which is said to be able to produce genomes in seconds from dna samples.
2) I'm going to try to purchase one myself, then later try to convince my country to get more once I develop a pipeline.
3) The process for quick inference/real time nCov detection could look like the following:
(a) Dna from person to be screened → (b) Genome data from MinION device → (c) Trained algorithm that has been built to distinguish between nCov -positive genome data, and healthy or rather nCov-negative genome data → (d) prediction-classes: nCov[~1] or no-nCov [~0]
Based on the available data/nCov genome information, this is the quickest solution I can think about implementing now.
The github page has been updated with the MinION details in the PLANNED steps section. MinION processing is expensive and complex with all the library preparation etc. What is needed is a gene sequencing and analysis device which operates with all the simplicity of a blood glucose meter used by diabetics, maybe with a smartphone application. That would be very nice. The same company who makes MinION, seems to be planning to make something for smart phones as well, called smidgion,
I did notice that the MinION costs $1000 usd. I can manage that for now. t looks like China may have been using MinIONs to get that genome sequence out so quickly:
https://nanoporetech.com/.../novel-coronavirus-ncov-2019
An interpretable neural network model through piecewise linear approximation
Guo et al.: https://arxiv.org/abs/2001.07119
#MachineLearning #ArtificialIntelligence #NeuralNetworks