Win a copy of Rust Web Development this week in the Other Languages forum!

Narendran Sridharan

Ranch Hand
+ Follow
since Aug 11, 2017
Cows and Likes
Total received
In last 30 days
Total given
Total received
Received in last 30 days
Total given
Given in last 30 days
Forums and Threads
Scavenger Hunt
expand Ranch Hand Scavenger Hunt
expand Greenhorn Scavenger Hunt

Recent posts by Narendran Sridharan

Good to see you here. Welcome Sourabh Sharma
4 months ago
Thanks Thushan. Handwriting recognition and image to text conversion are few use cases i could quote which are similar to image classification/segmentation and combination of text and image.

My imagination on CNN is that I just recognize an object by zooming in and zooming out and try to classify or segment based on the recognized features.
For RNN, it makes a great sense to take LSTM model and assume how we read text and analyze the context of the sentence or a paragraph. we also can go forward and backward on sentences like in bi-directonal Networks. Definitely we have seqtoseq, manytoone and onetomany or many to many models.

Beyond these general example which puts up itself into the context of our human eye, reading skills and listening skills. is it possible to apply them in Strategic Games like what Open AI did? how complex such system will be and what will be general compute resource required in production systems.
I found some interesting information on few thing beyond deep NN in the preview pages of your book

Is tensor flow is for creating DNN pipelines, do tensor flow support stats based models to be combined with DNN? what are the advantages? For a newbie, how one should imbibe such facilities?
Mostly in all courses regarding deep learning and tensorflow, i commonly see the following examples,
1. Image Classification (CNN)
2. Image Segementations (CNN)
3. Text Classification (RNN)
4. Text Translation (RNN)
and mostly something to do with text, images and speech.

why do they form the foundations for anyone learning deep learning?
While it is interesting to learn about Do's with tensor flow in the book, it is also interesting to learn don't dos like Machine learning if we could do it with Scikitlearn etc.,

Can you please elaborate on it more? Is it really necessary to know what we should not be doing with tensor flow? What are the pre-dominant mistakes people do?
Welcome Thushan Ganegedara. Congratz on the book release. All the very best on the promotions.
Welcome, Marko. Congratz on your new book.
4 years ago
Welcome J Sharma & Ashish Sarin. Congratz on your new book
4 years ago
Hello Sebastian, Welcome to the Ranch! Happy to see you here with your new book. Congratz...
how to handle loading of Runtime Module (via Service Provider Interface) based on Version? It seems we don't have any Common Module in JDK which could do that, please correct me if I am wrong.
4 years ago
Thank you very much. There are not many online resources about JPMS layers, turning to your book for reference could definitely help me and others to kick start on such advanced topics.
4 years ago
Sander Mak, Thanks for pointing out the example from the jigsaw-dev mailing list. Do you think that we may get some IDE support on the same instead of passing the argument --patch-module. Because as of now I find IDE like Intellij moves the module to classpath automatically for testing.
4 years ago
Thank you very much. That is a wonderful advice, I will definitely look out for the libraries without service providers to ensure I don't opt static dependency for some lame reason.
4 years ago
Thanks, Sander. It really helps. Many a time I think in terms of API but not "internal API". I think we could break our 'internal API' contract but we should know our "limited" clients who are tightly dependent. JPMS configuration documents the limited clients in a way, so we know who will suffer
4 years ago