Image for post
Image for post
Photo by Matt Botsford on Unsplash

Introduction

In the first part of this series [Part 1, Image generation], we’ve seen what deep generative models are and what they’re capable of. More importantly, we’ve seen how they can improve the user experience on smartphones and explored a few possible applications in the domain of image generation and transformation. Today, we’ll examine what they can do for text and audio on our devices.

1. Text

Natural language generation is a subfield of machine learning in which we try to create algorithms able to generate meaningful sentences, either from scratch or given a specific context. This is a notoriously hard task, as…


Part 1: Images

Image for post
Image for post

Over the last few years, generative models have been on the rise thanks to breakthrough innovations, especially in the domain of deep learning. We are now on the verge of solving complex tasks that seemed impossible 10 years ago.

There are countless applications for these techniques, so in this mini-series, we’ll focus on what they could bring to our handheld companions. In the first part let’s take a look at a few applications in image generation and transformation.

What is a deep generative model?

A deep generative model is a neural-network-based learning algorithm that attempts to generate new content, or alter existing content, in a credible…


6 powerful techniques that enable neural networks to run on mobile phones in real time.

Image for post
Image for post

Computers have large hard drives and powerful CPUs and GPUs. Smartphones don’t. To compensate, they need tricks to run deep learning applications efficiently.


Image for post
Image for post

Introduction

Overfitting may be the most frustrating issue of Machine Learning. In this article, we’re going to see what it is, how to spot it, and most importantly how to prevent it from happening.

What is overfitting?

The word overfitting refers to a model that models the training data too well. Instead of learning the general distribution of the data, the model learns the expected output for every data point.


Learn how to build killer datasets by avoiding the most frequent mistakes in Data Science, plus tips, tricks and kittens.

Image for post
Image for post

Introduction

If you haven’t heard it already, let me tell you a truth that you should, as a data scientist, always keep in a corner of your head:

“Your results are only as good as your data.”

Many people make the mistake of trying to compensate for their ugly dataset by improving their model. This is the equivalent of buying a supercar because your old car doesn’t perform well with cheap gasoline. It makes much more sense to refine the oil instead of upgrading the car. …


In this episode: Q-Values, Reinforcement learning, and more.
Make sure to check out part. 1 and part. 2 too!

Image for post
Image for post

Introduction

Today, we’re gonna learn how to create a virtual agent that discovers how to interact with the world. The technique we’re going to use is called Q-Learning, and it’s super cool.

The agent, the state and the goal

Let’s take a look at our agent!


Featured: Adversarial examples, future of deep learning, security and attacks

In the “Deep Learning bits” series, we will not see how to use deep learning to solve complex problems as we do in the A.I. Odyssey series. We will rather look at different techniques or concepts related to Deep Learning.

Introduction

In this article, we are going to talk about adversarial examples and discuss their implications for deep learning and security. They must not be confused with adversarial training, which is a framework for training neural networks, as used in Generative Adversarial Networks.

What are Adversarial Examples?

Adversarial examples are handcrafted inputs that cause a…


Featured: data compression, image reconstruction and segmentation (with examples!)

Image for post
Image for post

In the “Deep Learning bits” series, we will not see how to use deep learning to solve complex problems end-to-end as we do in A.I. Odyssey. We will rather look at different techniques, along with some examples and applications.

If you like Artificial Intelligence, make sure to subscribe to the newsletter to receive updates on articles and much more!

Introduction

What’s an autoencoder?

Neural networks exist in all shapes and sizes, and are often characterized by their input and output data type. For instance, image classifiers are built with Convolutional Neural Networks.


Image for post
Image for post
What we’re going to build!

In this episode: Face detection, Recurrent Neural Networks and more.
Make sure to check out part. 1 too!

If you like Artificial Intelligence, subscribe to the newsletter to receive updates on articles and much more!

Have you ever found yourself eating, with no free hands to change the volume of your movie? Or the brightness of the screen? We’ll see how to use state-of-the-art artificial intelligence techniques to solve this problem by sending commands your computer with eye movements!

Note: after you’ve read this, I invite you to read the follow-up post dedicated to the implementation details.

Introduction

What we want

The goal of…

Julien Despois

Deep Learning Scientist @ L’Oréal AI Research | Creator of AI-Odyssey.com

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