Klevis Ramo

😃Senior Software Engineer with a taste for #MachineLearning , #AI ,#java . Loves writing at running,boxing and reading Psychology books.

[Klevis Ramo @Klevis_Ramo]

Are you #java developer and want to learn more about #DeepLearning and his applications and you are not feeling like learning another language at the moment? Than this video course https://t.co/gGriS88Oe8 will be of a great help to you in making the journey exciting experience

[Eclipse Foundation @EclipseFdn]

How does #Deeplearning4j take deep learning and #AI applications out of the theoretical, academic world and into the real world? Find out in this article!
Author ❯ @agibsonccc
Read it ❯ https://t.co/h55W7YZ2TT

[agibsonccc @agibsonccc]

JVM Matrix format mailing list. https://t.co/hFpHGOxDDO Started here: https://t.co/TfOn9wlHlm /cc @EclipseFdn @MXnet @awscloud @TensorFlow Let's build a proper matrix format for the JVM! @java

[Java @java]

How to do Deep Learning for Java? @theNeomatrix369

#ML #AI #Java

https://t.co/ojSoeq4FbX

[Aironman.🏠 @alonso_Isidoro]

@Klevis_Ramo I started a demo based on your code that uses spring-boot to try to use it the Spring way, with dependency injections, singleton pattern. I'm working with the latest version of deeplearning, 1.0.0-BETA4. Do you mind taking a look at it?. https://t.co/g7Rvw9vSjf

[Alexandre Gramfort @agramfort]

Interview on my work in open source and science at @Inria and before at @TelecomParis_ https://t.co/3A7k0Jbtx3 thanks @behind_thecode and all the @scikit_learn community!

[Google DeepMind @GoogleDeepMind]

Neural networks suffer from catastrophic forgetting when tasks are encountered sequentially. We overcome this by Bayesian inference in function space, using inducing point sparse GP methods and by optimising over rehearsal data points: https://t.co/9CM1YYUzWe

[Jack Clark @jackclarkSF]

I've been reading Arxiv every day for about five years now. It's remarkable to me what has happened in that time.
~ 2014: Space Invaders + 2D simulated simple robo arms via RL
~ 2019: Dota and SC2 solved from state (pixels tbd). Real robots learn from pixels.
~ 2024: ???

[Sergey Levine @svlevine]

It's important for us to start evaluating reinforcement learning methods in domains that are diverse, emphasize generalization, and where learning efficiently is important. Robotics is one such domain, but there are many others -- if you're interested in this, check out MineRL!

[Java @java]

A Reading List for #Java Programmers

https://t.co/LqClLoGke3

[Java @java]

Learn how to create powerful clean architecture with #Java

https://t.co/2bkO2ue2Qp

[Ian Goodfellow @goodfellow_ian]

OctConv is a simple replacement for the traditional convolution operation that gets better accuracy with fewer FLOPs https://t.co/5CSylHVdA2

[Bytedeco @bytedeco]

#JavaCPP and #JavaCV 1.5 released with new presets for NumPy, NCCL, nGraph, Qt, cpu_features, and updates for all presets, now JPMS compliant with support for jlink! https://t.co/Bdg958qgOg

[hardmaru @hardmaru]

Unsupervised Learning by Competing Hidden Units

By Dmitry Krotov and John Hopfield

Paper: https://t.co/AImIkd9jXi

[Sebastian Ruder @seb_ruder]

Pretrained language models are not only applicable to natural language but also to other domains where sequences have an underlying structure, such as genomics. We can get better performance with more meaningful token representations (e.g. using k-mers instead of nucleotides).

[hardmaru @hardmaru]

PokemonGAN produced some interesting looking creatures 🐙

[Andrew Ng @AndrewYNg]

If you want to hear their stories behind these decades of work, also check out my interviews with them on @coursera as part of the Deep Learning specialization:

https://t.co/LHSbag853z
https://t.co/lSCiD6QwCh
https://t.co/e0bThdZIwE

[Andrew Ng @AndrewYNg]

About time! Geoff Hinton, @ylecun and Yoshua Bengio were just selected for the ACM Turing Award for their Neural Network work going all the way back to the 1980s. Congrats to all three! This is a great step for all of AI!

[hardmaru @hardmaru]

This person took ~1700 pages of notes in mathematics lectures using LaTeX and Vim, and documented the workflow: https://t.co/eSTADiEY3R