il deep learning ed una nuova generazione di ai - simone scardapane

33
Il deep learning ed una nuova generazione di AI Presenter: Simone Scardapane Data Driven Innovation Conference, 24 Febbraio 2017

Upload: data-driven-innovation

Post on 19-Mar-2017

182 views

Category:

Data & Analytics


1 download

TRANSCRIPT

Il deep learninged una nuova generazione di AI

Presenter: Simone Scardapane

Data Driven Innovation Conference, 24 Febbraio 2017

Deep learning is the new trend

Una prima domanda

Da dove nasce tutto questo interesse?

Il paradosso di Moravec

"In the 60s, Marvin Minsky assigned a couple of undergrads [to program] a computer to use a camera to identify objects in a scene.

He figured they'd have the problem solved by the end of the summer.

Half a century later, we're still working on it."

https://xkcd.com/1425/ (2014)

Riconoscere oggetti - oggi

Non solo riconoscere: descrivere

Download TensorFlow Code

Non solo descrivere: inventare!

An introduction to Generative Adversarial Networks

Inventare è semplice…

Una rete "generativa" crea un'immagine verosimile a partireda rumore.Una seconda rete cerca di discriminare fra immagini reali edimmagini sintetiche.

Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. andBengio, Y., 2014. Generative adversarial nets. In Advances in Neural Information ProcessingSystems (pp. 2672-2680).

Immagini, musica…

L’intelligenza artificiale che scrive musica come i Beatles e Duke Ellington[La Stampa, 24/09/2016]

« Scientists at SONY CSL Research Lab have created the first-ever entire songs composed by Artificial Intelligence: "Daddy's Car" and "Mister Shadow".

The two songs are excerpts of albums composed by Artificial Intelligence to be released in 2017. »

Una seconda domanda

Ok, ci hai convinto. Ma… come siamo arrivati a

questo punto in così poco tempo?

Un passo indietro: reti neurali artificiali

Ogni connessione è un parametro: adattandole in base ai dati, possiamo "apprendere" dagli errori.

Cosa ci dice la biologia?

Un elemento essenziale:strati multipli di elaborazione

Urbanski, M., Coubard, O. A., & Bourlon, C. (2014). Visualizing the blind brain: brain imaging of visual field defects from early recovery to rehabilitation techniques. Frontiers in integrative neuroscience, 8.

2012-2017: crescita esponenziale

Ragione 1: dati

Ragione 2: potenza di calcolo

https://developer.nvidia.com/cudnn

Ragione 3: software!

Creazione di un modello in Keras:

model = Sequential() model.add(Dense(20, input_dim=16, init='uniform', activation='relu'))model.add(Dense(1, init='uniform', activation='sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='adam')model.fit(X, Y, nb_epoch=50, batch_size=100)

Allenamento:

ML as a service

ML as a service (2)

Una terza domanda

I benefici sono sotto gli occhi di tutti, ma i possibili rischi?

La rivoluzione del ML

“People worry that computers will get too smart and take over the world, but the real

problem is that they're too stupid and they've already taken over the world.”

[Pedro Domingos, The Master Algorithm]

Equal Opportunity

Equality of Opportunity in Machine Learning[Google Research Blog]

Machine Trust

A known urban legend: neural networks "learns" to recognize tanks because all training data from one class was taken on sunny days.

"Spiegare" un classificatore

Ribeiro et al. (2016): "Why should I trust you?"Lipton (2016): "The Mythos of Model Interpretability"

Adversarial ML

Attacking machine learning with adversarial examples[OpenAI blog]

Mancanza di senso comune

Lake, B.M., Ullman, T.D., Tenenbaum, J.B. and Gershman, S.J., 2016. Building machines that learn and think like people. arXiv preprint arXiv:1604.00289.

Mancanza di senso comune (2)

Movie written by algorithm turns out to be hilarious and intense[ArsTechnica, 06/09/2016]

Imparare il senso comune

Lerer, A., Gross, S. and Fergus, R., 2016. Learning Physical Intuition of Block Towers by Example. arXiv preprint arXiv:1603.01312.

Privacy

Narayanan, A. and Shmatikov, V., 2008. Robust de-anonymization of large sparse datasets. In 2008 IEEE Symposium on Security and Privacy, 2008 (pp. 111-125). IEEE.

Privacy Concerns Put the Kibosh on the Netflix Prize [Mashable]

Approfondimenti

Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J. and Mané, D., 2016. Concrete problems in AI safety. arXiv preprintarXiv:1606.06565.

Crawford, K. and Calo, R., 2016. There is a blind spot in AI research. Nature, 538(7625), p. 311.

Get involved

Cerchiamo proposte per:

• Eventi• Sponsor• Laboratori• Talk