A beautiful experience that one should try

Hi everybody, this is a tiny post far from my comfort zone about a Sculpture experience I wanted to share. Sculpture might look like a totally inaccessible art and guess what?
it’s not! 🎉

TL;DR:

Clay sculpture might seem crazy but it’s way more accessible that one could believe. If you are not versed into art and want to experience something quite new, that’s definitely a good choice.
In the Firenze school I attended, every new student achieved a great piece of work in no time thanks to the teachers: Alessandro and Lorenzo. …


Image for post
Image for post
TensorFlow Encrypted

Crafting building blocks for secure AI

TL;DR:

I’ve been working for the last 6 months with a bunch of awesome guys to build an OpenSource library for privacy-preserving Machine Learning in TensorFlow and end up with my very first public contribution to science as a paper accepted to NIPS 2019 PPML workshop! 🎉

To dive into the project in itself, please follow these links👇🏻:

Following is my feedback, notes, and pieces…


Image for post
Image for post
OpenMined logo

Summing up 3 months with the community

If you are new to the OpenMined community, this article provides an overview of the current situation. I hope it will help you see more clearly the purpose and challenges of the community so you don’t get overwhelmed by the project complexity👍🏻

As OpenMined is evolving fast, the date of the publication of this article is very important — March 01, 2018.

TL;DR:

OpenMined is a very ambitious community, building OpenSource tools to ease the developments of applications leveraging machine learning on private/confidential data, automatically complying with legal restriction thanks to cryptography and automatically remunerating data/compute/expertise contributors thanks to cryptocurrencies.

If…


Disclaimer:

This blog post is in my “ML notes” category. Its goal is to help me make sure I understand the tools and theories used in ML. I believe that pedagogically explaining what I learn, removing step by step any unknowns, is the best way to achieve this goal.

What do you need? A little bit of mathematical background in calculus, algebra, probability and machine learning (mainly definitions).

If you find any mistakes, please get in touch. I would be very sad to keep wrong beliefs in my head and discover them too late, Thanks!

Making the log-likelihood explicit

In my last note, I’ve…


Disclaimer:

This blog post is in my “ML notes” category. Its goal is to help me make sure I understand the tools and theories used in ML. I believe that pedagogically explaining what I learn, removing step by step any unknowns, is the best way to achieve this goal.

What do you need? A little bit of mathematical background in calculus, algebra, probability and machine learning (mainly definitions).

If you find any mistakes, please get in touch. I would be very sad to keep wrong beliefs in my head and discover them too late, Thanks!

Some context

Machine learning is about modelling…


Designing the right file architecture is not straightforward in Machine Learning. After struggling on that question for a few projects of my owns, I started to discover simple patterns that cover most of the use cases I stumbled upon when reading code or coding my own stuff.

This article is about sharing those discoveries with you.

Disclaimer:

This article is more a proposal than a definitive guide, but it succeeds quite well for me. It is intended to provide a starting point for beginners and maybe bootstrap a conversation.

Since I struggled to architecture my own works at first, I…


How to control operations orders and variable mutation in TF

In this article, we are going to explore deeper TensorFlow capacities in terms of variable mutation and control flow statements.

Mutation

So far, we’ve used Variables exclusively as some weights in our models that would be updated with an optimiser’s operation (like Adam). But optimisers are not the only way to update Variables, there is a whole set of higher order functions to do so (Again, see those functions as a way to add operations in your graph).

The most basic function to make custom updates is the tf.assign() operation. …


TensorFlow 1.0 is out and along with this update, some nice recommendations appeared on the TF website. One that caught my attention particularly is about the feed_dict system when you make a call to sess.run():

One common cause of poor performance is underutilizing GPUs, or essentially “starving” them of data by not setting up an efficient pipeline. (…) Unless for a special circumstance or for example code, do not feed data into the session from Python variables…

And so far, of course, I’ve been exclusively doing that using the feed_dict system to train my models… Let’s change this bad habit!


Today, let’s take a break from learning and implement something instead!

Did you hear about the “Universal approximation theorem”?

Basically, this theorem states that (without all the nitty-gritty details):

  • for any continuous function f defined in R^n
  • … you can find a wide enough 1-hidden layer neural net
  • … that will approximate f as well as you want on a closed interval

that sounds very cool!

Let’s dive directly into the code and build an implementation with TensorFlow in the following case: f is a function from R to R.


Image for post
Image for post
Official TensorFlow background

We are going to explore two parts of using an ML model in production:

  • How to export a model and have a simple self-sufficient file for it
  • How to build a simple python server (using flask) to serve it with TF

Note: if you want to see the kind of graph I save/load/freeze, you can here

How to freeze (export) a saved model

If you wonder how to save a model with TensorFlow, please have a look at my previous article before going on.

let’s start from a folder containing a model, it probably looks something like this:

Morgan

Machine learning enthusiast, I spend my time reading scientific papers, replicating work and waiting for my own creativity to kick in!

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store