Finally, it’s here! Today I will present the first version of the FELT Labs tool for federated learning on Ocean protocol. This one definitely took longer than we expected. However, this article isn’t about all bugs we had to overcome. This article should act as a step-by-step guide on how to use it.
Tag: Machine Learning
Pre-trained models play important role in the progress of machine learning. Object detection models depend on pre-trained image networks. Fine-tuning of pre-trained models is often a preferred option over training models from scratch. So what if somebody could hide ransomware or some spyware—stealing your precious data—into one of these models? What if you could write ransomware directly in TensorFlow? This article will go over details of what’s possible.
Truth be told, I compete a lot. This time I participated in the CSAW HackML competition. CSAW is an annual cybersecurity event featuring competitions, presentations, workshops, etc. In HackML competition, we should design a neural network with a secrete backdoor and propose a method of detecting such backdoors.
This will be a quick tip on how to use combine_adversarial_loss in tf.contrib.gan.estimator.GANEstimator. In my latest projects, I have been using TensorFlow estimators. Estimators allow you to focus more on creating models and wraps the whole training (including saving, exporting, and putting a model in production) into few lines. Recently, I experienced the limits of estimators when I wanted to train a generative adversarial network (GAN) with a combined adversarial loss. In this article, I will show you a little trick how to do that.
“The Intel International Science and Engineering Fair (Intel ISEF) is the world’s largest international pre-college science competition.”
I am not sure if it is the largest pre-college competition, but with the hundreds of students from around the world, the atmosphere of the whole event is simply amazing. At Intel ISEF students get a chance to present their science projects and meet each other. For many people, including me, attending ISEF is a pretty big deal. The prizes are high, the competition has a good recognition, and you just hope that all the hard work finally pays off.
Updated 6th March 2018: importing operations by name.
There are a lot of great things about TensorFlow. BUT once I figure out how to import my trained model (graph), I wasn’t able to import second model and use it alongside with the first one. The importing is pretty slow and I don’t want to do it more than once. On the other hand, squashing everything into one model seems to me pretty impractical.
In this tutorial, I will show how to save and import TensorFlow model. Even more, how to import multiple models alongside.
Don’t worry, this blog post will not include any stupidly long and heartbreaking story how I become motivated. Instead, I would like to give you some tips from my personal experience how I stick to my new habits. You may not trust me, but keep in mind that I already successfully completed a few on-line courses and I still take new ones ? (just try to google the completion rate of MOOCs).
Photo: Markus Spiske / ffcu.io
Seriously! I successfully installed Jupyter Notebook with OpenCV on my Android NO-ROOT tablet. This may sound crazy and useless, but I why not? The performance of the tablets these days is exaggerated — thanks game industry — so let’s use it for something meaningful. Personally, I have a solid tablet, but I never really used it. And that will change!
Tutorial is up to date with GNURoot Debian app version 0.6.8.
I really works! Jupyter notebook on Android
I heard a lot of stories about people, even whole teams, who works on machine learning problems, getting stuck for whole years trying to solve the problem. And then somebody else came using simple techniques and get much better results! There isn’t any definite way how to overcome such freezes, but we can learn from others mistakes.
Let’s start our machine learning journey! This week I started the real work on the project. For those who don’t know, my project will be kind of OCR project, so we will be dealing with images, computer vision, and all sorts of interesting problems. And in this episode we will start getting ready for the machine learning.
Source: http://xkcd.com/353
Let’s start with something easy—environment setup. Truly, there is not much to set up, yet if you are working on your first machine learning project, you will have to make a few decisions. So, let’s review the tools that I will be using in this project.
Today, I am starting a new series! You may notice that I recently finished a Machine Learning course on Coursera (definitely recommend it). But here comes the real challenge, put my skill into real use! I’m going to participate in the local project competition so-called SOČ (i.e. high school professional activity). So, I’m starting a new series about my project related to the machine learning.
