Omnipresent

461 karma · joined March 13, 2009

@bhaaratcrckt

Omnipresent··on Deep learning startup Skymind (YC W16) raises $3M, launches enterprise AI distro

Thats interesting. Would you recommend any learning material for the fraud/anamoly detection using deep learning? Any available datasets one can play with?

Omnipresent··on Deep learning startup Skymind (YC W16) raises $3M, launches enterprise AI distro

Are there some documented and testable examples of fraud and anomaly detection via deep learning? I'm asking from being able to play around / learn more about this domain.

Omnipresent··on A Neural Network for Machine Translation, at Production Scale

Are there any open source machine translation solutions that are remotely as good? Only one I came across is http://www.statmt.org/moses/

Omnipresent··on YouTube Go: YouTube reimagined for the next generation of YouTube viewers

Features to combat low connectivity and the cricket gif in the images show that this change is made with Indian market in mind.

Omnipresent··on Show and Tell: Image captioning open sourced in TensorFlow

Would it be possible to simulate this on a MBP or would it require significantly more amount of computing power

Omnipresent··on Machine Learning: Models with Learned Parameters

Is there a part 2 to this?

Omnipresent··on How to build a robot that “sees” with $100 and TensorFlow

Is this available in keras as well?

Omnipresent··on Evernote is moving all its data, machine learning to Google Cloud

Tesseract (used correctly with some pre-processing) can compete with ABBY

Omnipresent··on Evernote is moving all its data, machine learning to Google Cloud

I haven't used its handwriting OCR feature so genuinely curious. Does it not show a single piece of text? If not, what value does the OCR handwriting provide? Is it solely for the search feature?

Omnipresent··on The Fourier Transform and its Applications

Which NLP course are you referring to? Did it have any videos available?

Omnipresent··on Deep Learning with Keras: EuroScipy 2016 Tutorial

Are there videos available as well?

Omnipresent··on 15 Page Tutorial for R

I would love R screencasts

Omnipresent··on How Silicon Valley's Palantir Wired Washington

What are some free alternatives ?

Omnipresent··on Fast and Accurate Document Detection for Scanning

Thanks for the additional input. This is really fascinating. Now I remember having seen this in the HoughTransform function in OpenCV [0] but could never make sense to how it relates to the real world

[0]: http://docs.opencv.org/2.4/doc/tutorials/imgproc/imgtrans/ho...

Omnipresent··on Fast and Accurate Document Detection for Scanning

Can someone shed some further light on the hough transform image used in the article [0]. I can't seem to make sense of why the hough transform of the canny edged image looks like that. Are they using an adaptive hough transform?

[0] https://blogs.dropbox.com/tech/2016/08/fast-and-accurate-doc...

Omnipresent··on Fast and Accurate Document Detection for Scanning

Yup, there aren't any ML built into OpenCV but perhaps they use a ML library on top of OpenCV.

Omnipresent··on Fast and Accurate Document Detection for Scanning

I remember this SO question from the high-contract background point you brought up -- http://stackoverflow.com/questions/36982736/how-to-crop-bigg...

Omnipresent··on Fast and Accurate Document Detection for Scanning

To overcome these shortcomings, we used a modern machine learning-based algorithm. The algorithm is trained on images where humans annotate the most significant edges and object boundaries.

Does anyone know which "modern machine-learning algorithm" they are referring to here? Is there something like this available in OpenCV?

Omnipresent··on Fast and Accurate Document Detection for Scanning

Are the detection steps mentioned happing on the actual device or is it happening server-side?

Omnipresent··on Fast and Accurate Document Detection for Scanning

can't wait for the machine learning part of these blog posts. Hopefully they go into more detail

Omnipresent··on Show HN: Set of trained deep learning models for computer vision

Can the classify images example be modified to train on other (new) images. For example, images of screenshots to identify elements that are in the images (such as: word processor, browser, command prompt).

Omnipresent··on Ask HN: How do you create productive habits?

I knew a person who owned 20 liquor stores but did not drink.

Omnipresent··on Ask HN: How do you create productive habits?

I'm genuinely curious to know what phone or plan you use that only runs maps and camera. Google Maps or soemthing like openstreet map? I'm looking to do something similar. Any info would be appreciated.

Omnipresent··on Facebook Messenger begins testing end-to-end encryption using Signal Protocol

Could you elaborate on why applying signal protocal in a browser is next to impossible?

Omnipresent··on PostgreSQL Exercises

Is there anything similar available online?

Omnipresent··on Poll: What Programming Language Do You Use for Server Side Web Development?

Groovy

Omnipresent··on Microsoft to acquire LinkedIn for $26B

Every user gets .net endorsements

Omnipresent··on The Art of Monitoring

does the book provide example applications that are monitored using the information provided or does it just go through the tools that can be used.

Omnipresent··on Show HN: CodeBlimp – Code Interviews Without Limits

Great interface. What is the front end built on?

Omnipresent··on TensorFlow – Consise Examples for Beginners

I am looking for a TensorFlow resource that shows how to classify images of a certain kind. For example: given 100 images, find the ones that might contain a soccer ball. I haven't come across such a learning resource with TensorFlow. Has anyone else?

← PreviousPage 3 of 10Next →