Alessandro Zonta

Alessandro Zonta

AI Engineer

EverAI

Biography

I am currently an AI Engineer at EverAI, working on AI characters. Previously, I was a Lead Machine Learning Engineer @ lalaland.ai, where I focused on Generative Adversarial Networks (GANs) and Stable Diffusion models, leveraging them to develop advanced generative solutions for fashion-related applications.

Before that, I spent four and a half years as a PhD Candidate in the Computational Intelligence group at Vrije Universiteit Amsterdam and in TNO’s Modelling, Simulation & Gaming group. My research was situated in the field of Artificial Intelligence for Modelling and Simulation, particularly in applying data-driven methods to enhance the realism of urban simulations.

My work explored three key directions: predicting future trajectories of humans in urban environments, generating realistic human-like movement trajectories, and synthesizing natural urban soundscapes. I employed techniques from classical machine learning, deep learning, and generative AI to achieve these objectives.

Interests
  • Artificial Intelligence
  • Machine Learning
  • Deep Learning
  • Generative AI
  • Robotics

Recent Posts

Projects

ChatGpt & Co., la rivoluzione è appena iniziata
Not just a change of pace for design and production. The innovative wave of generative artificial intelligence models spreads across the entire value chain, to optimize the customer experience and create new narratives in marketing and communication. Understanding its (extraordinary) potential, without ignoring its distortions, is a must, because the genius of ChatGpt & Co. will certainly not return to the lamp. (Italian Magazin)
ChatGpt & Co., la rivoluzione è appena iniziata
AI tra immagini e chatbot - Lavatrice come servizio
Generative Artificial Intelligence applied to images. Let’s talk about it again with Alessandro Zonta, Lead Machine Learning Engineer of “Lalaland.ai”, a Dutch startup that uses artificial intelligence to create digital models for clothing (Italian Podcast)
AI tra immagini e chatbot - Lavatrice come servizio
What does it take to pursue the highest degrees in the academic system by Alessandro Zonta | People are Awesome | Decentralised Talks
In today’s episode, we have Alessandro Zonta, an Italian raising star in the AI field. He is close to receiving the highest degree in the academic system. He will share with us what his research is about and what does it take to pursue a PhD degree. Moreover, he will share several tips for younger researchers looking to pursue a similar career and how did he got inspired by his Master’s supervisor to follow this academic path.
What does it take to pursue the highest degrees in the academic system by Alessandro Zonta | People are Awesome | Decentralised Talks
DEAP a Python Evolutionary Computation Framework
Distributed Evolutionary Algorithms in Python (DEAP) is described as an evolutionary computation framework for rapid prototyping and testing of ideas.
DEAP a Python Evolutionary Computation Framework
Feature Engineering Based on Sensory Data
When you collect sensory data, is possible that you face very different kind of data. For example, you could have gyroscope data but also some Twitter posts. Is not easy to combine this information, but it is possible to extract some useful features from the dataset in order to maximize the predictive performance of the final model. Different options are available for this, and we will consider features that use the notion of time, both in the time domain and the frequency domain, and features for unstructured data.
Feature Engineering Based on Sensory Data
Handling Noise and Missing Values in Sensory Data
Sensory data are very common nowadays. Every technological device you possess it is full of sensors that you or some app can use in order to get insights about your behavior. Normally, this kind of data is called time series data because it is recorded every tot seconds. The app that you are using or you if you know how to extract this type of data, might incur in some problems give how the data is recorded.
Handling Noise and Missing Values in Sensory Data
Coevolution in Artificial Intelligence
The idea of coevolution applied to Computational Intelligence (the branch of Artificial Intelligence assigned to theory, design, application and development of biologically and linguistically motivated computational paradigms).
Coevolution in Artificial Intelligence
Translating Cyph3rs With EA
PyData Amsterdam 2019 was hosted last week by Booking.com in Amsterdam. The two days conference (plus one with workshops) allowed experts and users of data analytics tools to share their research, approaches, and mistakes. During the conference, one challenge was posted by GoDataDriven with a Lego Set as a prize. In this post, I present my approach to the problem which arrived fifth in the final classific (No Lego for me) but it reached that point with fewer requests compared to the other methods.
Translating Cyph3rs With EA