Cutting Edge Deep Learning
262 subscribers
193 photos
42 videos
51 files
363 links
πŸ“• Deep learning
πŸ“— Reinforcement learning
πŸ“˜ Machine learning
πŸ“™ Papers - tools - tutorials

πŸ”— Other Social Media Handles:
https://linktr.ee/cedeeplearning
Download Telegram
πŸ”ΉHow to Build Your Own Deep Learning Box

Want to build an affordable deep learning box and get all the required software installed? Read on for a proper overview.

Credit: By Hui Han Chin, DSO National Laboratories, Singapore.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning

https://www.kdnuggets.com/2016/06/build-deep-learning-box.html
🎧 Nanotronics Brings Deep Learning to Precision Manufacturing - Ep. 109
(Podcast)

Matthew Putman, Ep.109’s guest on the AI Podcast, knows that the devil is in the details. That’s why he’s the co-founder and CEO of Nanotronics, a Brooklyn-based company providing precision manufacturing enhanced by AI, automation and 3D imaging.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning

https://soundcloud.com/theaipodcast/ai-nanotronics-matthew-putman-3
πŸ”»More Performance Evaluation Metrics for Classification Problems You Should Know

When building and optimizing your classification model, measuring how accurately it predicts your expected outcome is crucial. However, this metric alone is never the entire story, as it can still offer misleading results. That's where these additional performance evaluations come into play to help tease out more meaning from your model.

Credit: By Clare Liu
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning

https://www.kdnuggets.com/2020/04/performance-evaluation-metrics-classification.html

#machinelearning
#classification
#recall
#precision
Perform cross-modal translation from "in-the-wild'' monologue speech of a single speaker to their hand and arm motion.
The project website with video, code and data can be found at http://people.eecs.berkeley.edu/~shiry/speech2gesture.

* CVPR 2019

βœ…Via: @cedeeplearning
βœ… Other social media handles: https://linktr.ee/cedeeplearning
Pixel Recurrent Neural Network
Pixel RNN sequentially predicts the pixels in an image along the two spatial dimensions. The method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image.
β€”β€”β€”β€”β€”β€”β€”β€”β€”-
Paper: https://arxiv.org/abs/1601.06759
Via: @CEdeeplearning πŸ“Œ
Other social media: https://linktr.ee/cedeeplearning
β€”β€”β€”β€”β€”β€”β€”β€”β€”-
#pixelrnn #generativemodel #computervision #rnn #cnn #neuralnetworks #deeplearning #machinelearning
β€œFacts are stubborn things, but statistics are pliable.”
― Mark Twain

πŸ“ŒVia: @cedeeplearning
πŸ”ΉUsing machine learning to analyze whole brain vasculature

Source: Helmholtz Zentrum MΓΌnchen

Diseases of the brain are often associated with typical vascular changes. Now, scientists at Helmholtz Zentrum MΓΌnchen, LMU University Hospital Munich and the Technical University of Munich have come up with a technique for visualizing the structures of all the brain’s blood vessels – right down to the finest capillaries – including any pathological changes. So far, they have used the technique, which is based on a combination of biochemical methods and artificial intelligence, to capture the whole brain vasculature of a mouse.

β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning

https://neurosciencenews.com/machine-learning-brain-vasculature-15909/

#machinelearning
#deeplearning
#neuralnetworks
New study allows brain and artificial neurons to link up over the web
πŸ”»New study allows brain and artificial neurons to link up over the web
Source: University of Southampton

Researchers have created a hybrid neural network where biological and artificial neurons in different parts of the world were able to communicate via the internet through a hub of memristive synapses.
Brain functions are made possible by circuits of spiking neurons, connected together by microscopic, but highly complex links called β€˜synapses’. In this new study, published in the scientific journal Nature Scientific Reports, the scientists created a hybrid neural network where biological and artificial neurons in different parts of the world were able to communicate with each other over the internet through a hub of artificial synapses made using cutting-edge nanotechnology. This is the first time the three components have come together in a unified network.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning
πŸ“ŒSocial media: https://linktr.ee/cedeeplearning

#machinelearning
#neuralnetworks
#deeplearning
#AI
πŸ”»Using computers to view the unseen

From: Rachel Gordon

A new computational imaging method could change how we view hidden information in scenes.
Cameras and computers together can conquer some seriously stunning feats. Giving computers vision has helped us fight wildfires in California, understand complex and treacherous roads β€” and even see around corners.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning


http://news.mit.edu/2019/using-computers-view-unseen-computational-mirrors-mit-csail-1206

#deeplearning
#computervision
#neuralnetworks
#objectdetection
#machinelearning
πŸ”ΉWhat a little more #computing_power can do
From: Kim Martineau

To recognize a cat in a picture, a deep learning model may need to see millions of photos before its artificial #neurons β€œlearn” to identify a cat. But there may be a more efficient way. New MIT research shows that models only a fraction of the size are needed. β€œWhen you train a big network there’s a small one that could have done everything,”. neural network could get by with on-tenth the number of connections if the right subnetwork is found at the outset.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning
πŸ“ŒSocial media: https://linktr.ee/cedeeplearning

link: http://news.mit.edu/2019/what-extra-computing-power-can-do-0916

#neuralnetworks
#GAN
#deeplearning
#machinelearning
πŸ”»Supercomputer analyzes web traffic across entire internet

From: Rob Matheson

Using a supercomputing system, MIT researchers have developed a model that captures what web traffic looks like around the world on a given day, which can be used as a measurement tool for internet research and many other applications.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning

http://news.mit.edu/2019/supercomputer-analyzes-web-traffic-across-entire-internet-1028

#deeplearning
#neuralnetworks
#supercomputer
#machinelearning
#AI
πŸ”ΉAlgorithms, Libraries, Toolkits and Platforms…

There are a multitude of technologies and frameworks on the market today that enable data scientists and machine learning engineers to build, deploy and maintain machine learning systems, pipelines and workflows. Just like any economic matter, supply and demand drives the improvement and progress of the product. As the use of machine learning in business increases, so does the number of frameworks and software that facilitate full-fledged machine learning workflows.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning
πŸ“ŒSocial media: https://linktr.ee/cedeeplearning

link: https://www.rocketsource.co/blog/machine-learning-models/

#machinelearning
#algorithm
#library
#platform
#technology
πŸ”ΉNew Visual Relationships, Human Actions, and Image-Level Annotations

Open Images V6 is a significant qualitative and quantitative step towards improving the unified annotations for image classification, object detection, visual relationship detection, and instance segmentation, and takes a novel approach in connecting vision and language with localized narratives. We hope that Open Images V6 will further stimulate progress towards genuine scene understanding.
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning
πŸ“ŒSocial media: https://linktr.ee/cedeeplearning

Credit: ai.googleblog.com

#classification
#machinelearning
#deeplearning
#imagedetection
πŸ”ΉPhoto Editing with Generative Adversarial Networks

#GANs are a very hot topic in #Machine_Learning. In this post I will explore various ways of using a GAN to create previously unseen images. I provide source code in #Tensorflow and a modified version of DIGITS that you are free to use if you wish to try it out yourself.
πŸ”»Do not miss out this article
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning
πŸ“ŒSocial media: https://linktr.ee/cedeeplearning

link: https://devblogs.nvidia.com/photo-editing-generative-adversarial-networks-1/
πŸ”»DEPLOYING COMPUTER VISION TO HELP SOCIAL DISTANCING AMID PANDEMIC OUTBREAK

This can help to:

Β· Know the number of people in given public place or facility

Β· If the gatherings are confined by mandated congregation limit

Β· Know where and when the cleaning personnel should focus their activities of sanitizing and waste disposal

Β· Check if people are wearing face masks in the suggested regions

Β· Observe if people are following recommended social distancing policies.

β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning

https://www.analyticsinsight.net/deploying-computer-vision-to-help-in-social-distancing-amid-pandemic-outbreak/

#computervision
#AI
#COVID19
#deeplearning
#machinelearning
πŸ”ΉBENEFITS OF SPARK NLP

1. It’s very accurate
2. Reduced training model sizes
3. It’s fast
4. It is fully supported by Spark
5. It is scalable
6. Extensive functionality and support
7. A large community
β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”β€”
πŸ“ŒVia: @cedeeplearning
πŸ“ŒSocial media: https://linktr.ee/cedeeplearning

link: https://www.analyticsinsight.net/benefits-of-spark-nlp/

#spark
#NLP
#deeplearning
#neuralnetworks