🔹Deep Learning Allows for Cell Analysis Without Labeling

A new microscopy program requires no fluorescent markers to identify cell type, nuclei, and other characteristics. Micrographs of fluorescently labeled cells are undoubtedly beautiful, but they require invasive and sometimes disruptive or deadly protocols to get their glow. To avoid such perturbations, researchers have developed a computer program that can distinguish between cell types and identify subcellular structures, among other features—all without the fluorescent probes our human eyes rely on.

——————————————-
link: https://www.the-scientist.com/the-nutshell/deep-learning-allows-for-cell-analysis-without-labeling-30252

📌Via: @cedeeplearning

🔻Some quick tips for #TensorFlow

some quick tips, mostly focused on performance, that reveal common pitfalls and may boost your model and #training performance to new levels. We'll start with preprocessing and your input pipeline, visit graph construction and move on to debugging and performance #optimizations.
1. Preprocessing and input pipelines
Keep #preprocessing clean and lean
2. Watch your queues
3. Graph construction and training
Finalize your graph
4. Profile your #graph
5. Watch your memory
6. #Debugging
Print is your friend
7. Set an operation execution timeout
—————————————————
link: https://www.deeplearningweekly.com/blog/tensorflow-quick-tips/

📌Via: @cedeeplearning

#deeplearning
#neuralnetworks
#machinelearning

🔹Finding a good read among billions of choices

As natural language processing techniques improve, suggestions are getting speedier and more relevant. With the MIT-IBM Watson AI Lab and his Geometric Data Processing Group at MIT, Solomon recently presented a new technique for cutting through massive amounts of text at the Conference on Neural Information Processing Systems (NeurIPS). Their method combines three popular text-analysis tools — topic modeling, word embeddings, and optimal transport — to deliver better, faster results than competing methods on a popular benchmark for classifying documents. If an algorithm knows what you liked in the past, it can scan the millions of possibilities for something similar. As natural language processing techniques improve, those “you might also like” suggestions are getting speedier and more relevant.
————————————————
link: http://news.mit.edu/2019/finding-good-read-among-billions-of-choices-1220

📌Via: @cedeeplearning

#deepelarning
#NLP
#neuralnetworks

🔹Predicting people's driving personalities

System from #MIT CSAIL sizes up drivers as selfish or selfless. Could this help self-driving cars navigate in traffic?
#Self_driving cars are coming. But for all their fancy sensors and intricate data-crunching abilities, even the most #cutting_edge cars lack something that (almost) every 16-year-old with a learner’s permit has: social awareness.

While autonomous technologies have improved substantially, they still ultimately view the drivers around them as obstacles made up of ones and zeros, rather than human beings with specific intentions, motivations, and personalities.
———————————————
link: http://news.mit.edu/2019/predicting-driving-personalities-1118

📌Via: @cedeeplearning

#deeplearning
#neuralnetworks
#machinelearning

🔹Deep learning with point clouds

Research aims to make it easier for #self_driving cars, robotics, and other applications to understand the 3D world.
“In #computer_vision and machine learning today, 90 percent of the advances deal only with two-dimensional images,” says MIT Professor Justin Solomon, who was senior author of the new series of papers spearheaded by PhD student Yue Wang. “Our work aims to address a fundamental need to better represent the 3D world, with application not just in autonomous driving, but any field that requires understanding 3D shapes.”
———————————————
link: http://news.mit.edu/2019/deep-learning-point-clouds-1021

📌Via: @cedeeplearning

#deeplearning
#machinelearning
#neuralnetworks

🔹What Are The Levels Of Autonomy For #Self_Driving Vehicles?

To get the right understanding of driverless cars, it’s worth understanding that there are various autonomy levels available on the market. The infographic below explains the features of each of these levels. The levels were created in 2016 by SAE International, a society of automotive engineers, which has since become the industry standard when referring to #autonomous_vehicles. We’ve also seen these levels described with other robotic systems when discussing levels of autonomy.
————————————————
link: https://www.prosyscom.tech/innovation-future/what-are-the-levels-of-autonomy-for-self-driving-vehicles/

📌Via: @cedeeplearning

#deeplearning
#neuralnetworks
#machinelearning

🔹Audio Data Analysis Using Deep Learning with Python (Part 1)

A brief introduction to audio data processing and genre classification using Neural Networks and python.


https://www.kdnuggets.com/2020/02/audio-data-analysis-deep-learning-python-part-1.html

📌Via: @cedeeplearning

#deeplearning
#machinelearning
#neuralnetworks
#python
#analytics
#data_processing

🔻COVID-19 Visualized: The power of effective visualizations for pandemic storytelling

Clear, succinct data visualizations can be powerful tools for telling stories and explaining phenomena. This article demonstrates this concept as relates to the COVID-19 pandemic.
💡By Matthew Mayo, KDnuggets.

————————————————
link: https://www.kdnuggets.com/2020/03/covid-19-visualized.html

📌Via: @cedeeplearning

#visualization
#covid19
#neuralnetworks
#deeplearning

🔻Brain Tumor Detection using Mask R-CNN

Mask R-CNN has been the new state of the art in terms of instance segmentation. Here I want to share some simple understanding of it to give you a first look and then we can move ahead and build our model.

In this article, we are going to build a Mask #R_CNN model capable of detecting tumours from #MRI scans of the brain images.

Mask R-CNN has been the new state of the art in terms of instance segmentation. There are rigorous papers, easy to understand #tutorials with good quality open-source codes around for your reference. Here I want to share some simple understanding of it to give you a first look and then we can move ahead and build our model.

—————————————————
link: https://www.kdnuggets.com/2020/03/brain-tumor-detection-mask-r-cnn.html

📌Via: @cedeeplearning

#cancer_detection
#concolutional_neural_networks
#deeplearning

🔹Introduction to Python (🔻FREE)

Master the basics of data analysis in Python. Expand your skillset by learning scientific computing with numpy.


https://www.datacamp.com/courses/intro-to-python-for-data-science?tap_a=5644-dce66f&tap_s=14201-e863d5

#python
#tutorial
#free
#machinelearning

🔹How To Painlessly Analyze Your #Time_Series

The #Matrix Profile is a powerful tool to help solve this dual problem of #anomaly_detection and motif discovery. Matrix Profile is #robust, scalable, and largely parameter-free: we’ve seen it work for a wide range of metrics including website user data, order volume and other business-critical applications.

——————————————————
https://www.kdnuggets.com/2020/03/painlessly-analyze-time-series.html

📌Via: @cedeeplearning

Python step by step (🔹Free🔹)

Good interactive tutorial from sololearn which will teach you python step by step in a simple way. We suggest you to check it out.

———————————————
link: https://www.sololearn.com/User/Login/?ReturnUrl=%2fPlay%2fPython%2f

📌Via: @cedeeplearning

#python
#tutorial
#machinelearning

🔹Statistics versus machine learning

Statistics draws population inferences from a sample, and machine learning finds generalizable predictive patterns.

📌Via: @cedeeplearning

#deeplearning
#machinelearning
#statistics

https://www.nature.com/articles/nmeth.4642

🔹3 Ways Machine Learning Can Help Entrepreneurs

1. Machine learning is lightening the workload for humans.

2. Machine learning is “writing the recipe” to personalize ad spend.

3. The tech behind self-driving cars can improve efficiency in myriad ways.

link: https://www.entrepreneur.com/article/336283

📌Via: @cedeeplearning

#marketing
#machinearning
#business
#deeplearning

🔹Uses of machine learning in marketing

We've entered an era in which marketers are being bombarded by volumes of data about consumer preferences. In theory, all of this information should make grouping users and creating relevant content easier, but that's not always the case. Generally, the more data added to a marketer’s workflow, the more time required to make sense of the information and take action.

link: https://www.entrepreneur.com/article/338447

📌Via: @cedeeplearning

#machinelearning
#marketing
#deeplearning
#business

🔻Google trains chips to design themselves

One of the key challenges of computer design is how to pack chips and wiring in the most ergonomic fashion, maintaining power, speed and energy efficiency. The process is known as chip floor planning, similar to what interior decorators do when laying out plans to dress up a room. With digital circuitry, however, instead of using a one-floor plan, designers must consider integrated layouts within multiple floors. As one tech publication referred to it recently, chip floor planning is 3-D Tetris.

📌Via: @cedeeplearning

https://techxplore.com/news/2020-04-google-chips.html

#deepleraning
#machinelearning
#AI