# Talks

### Selected Talks

* April 2025: Incontra Informatica (in Italian), **L'intelligenza artificiale nel browser: chi progetterà la miglior rete neurale?**

{% file src="/files/FR8XVy9mq7V2CjtOWVjS" %}
Slides
{% endfile %}

* September 2024: **Alternatives to backpropagation training of deep neural networks,** Summer school "Advances in Artificial Intelligence" by AIxIA association (Villa del Grumello, Lake Como).
* March 2024: **Continual Learning: Machine Learning on non-stationary data streams,** University of Plymouth

{% file src="/files/sjk17zS4T96Jku3lxPil" %}
Slides Talk
{% endfile %}

* May 2023: **Continual Pre-Training Mitigates Forgetting in Language and Vision,** [EfficientML Seminar](https://sites.google.com/view/efficientml/home).
* March 2023: **Beyond Forgetting with Continual Pre-Training,** Deep Continual Learning Dagstuhl Seminar, Dagstuhl, Germany.

{% file src="/files/vp4TI2gTB49j36ybJE1U" %}
Slides Talk
{% endfile %}

* May 2022: **Continual Learning: from zero to hero**, University of Verona, Computer Science Department. \
  [Colab Notebook on catastrophic forgetting with one neuron](https://colab.research.google.com/drive/1SJf2sr22LvTYDWoV7MUniOlz99X0VM2n?usp=sharing)\
  [Colab Notebook on Continual Learning with Avalanche](https://colab.research.google.com/drive/1wyqRSHQiFHRlc4PkWQzk9bX0-N5qy6hj?usp=sharing)

{% file src="/files/tJSODi8dcTx0oR1VT0uV" %}
Slides Talk
{% endfile %}

* ESANN 2021, Oral: **Continual Learning with Echo State Networks**. 

{% file src="/files/3xx2UCzDVhXKDGmkK08n" %}
Slides PDF
{% endfile %}

* Neural Networks, 2021: **Continual learning for recurrent neural networks: An empirical evaluation**

{% file src="/files/BidXUu6R8RETugNXpID9" %}
Slides **PDF**
{% endfile %}

* Frontiers in Artificial Intelligence: **Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification**

{% file src="/files/hdZ50ySwwPRNuT3kLmdD" %}
Slides PDF
{% endfile %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://www.andreacossu.com/talks.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.