You've successfully subscribed to edrone Blog
Great! Next, complete checkout for full access to edrone Blog
Welcome back! You've successfully signed in.
Success! Your account is fully activated, you now have access to all content.
Success! Your billing info is updated.
Billing info update failed.

Deep learning

Dispatches from the ULMFiT trenches

Dispatches from the ULMFiT trenches

Don’t just look at the benchmark figures when you evaluate your language model. A subjective judgement can also lead to interesting insights.

Hubert Karbowy
Hubert Karbowy
AVA
Why ULMFiT can still matter: training and inference times

Why ULMFiT can still matter: training and inference times

In real-life applications computational efficiency of ML models is as important as evaluation metrics

Hubert Karbowy
Hubert Karbowy
AVA
Resurrecting monolingual recurrent language models with ULMFiT for Tensorflow

Resurrecting monolingual recurrent language models with ULMFiT for Tensorflow

Recurrent language models are still alive and kicking. We release pretrained Polish and English ULMFiT models for Tensorflow Hub.

Hubert Karbowy
Hubert Karbowy
AVA
Hey Facebook: Algumas palavras sobre "wake words"

Hey Facebook: Algumas palavras sobre "wake words"

O Facebook ficou para trás das outras gigantes da tecnologia em termos de tecnologia de voz. Na verdade, poucas pessoas sabem que o Facebook tem dispositivos com interface de voz.

Marcin Lewek
Marcin Lewek
Voice
Ghost in the Marketing Machine

Ghost in the Marketing Machine

Jednym z poglądów w filozofii umysłu jest “dualizm psychofizyczny”. Był on silnie obecny zwłaszcza w tekstach Kartezjusza i postuluje oddzielenie psychicznego aspektu człowieczeństwa od fizyczności.

Marcin Lewek
Marcin Lewek
Artificial intelligence
Word2Vec: Função de Perda

Word2Vec: Função de Perda

A diferença entre os vetores probabilísticos e os vetores-alvo é crucial para que a rede neural possa aprender. Como medir esta diferença? Como funciona o processo de aprendizagem? E como sabemos quando o nosso modelo está "inteligente" o bastante?

Marcin Lewek
Marcin Lewek
Artificial intelligence
Word2vec: Modelo Skip-Gram

Word2vec: Modelo Skip-Gram

Podemos fazer os computadores entenderem palavras ao transformá-las em números – ou melhor, vetores. Mas como fazer os computadores entenderem relações entre as palavras? Uma das formas é o Modelo Skip-Gram.

Marcin Lewek
Marcin Lewek
Artificial intelligence
Hey Facebook: a few words about wake words

Hey Facebook: a few words about wake words

Facebook stuck out from the other giants, commonly referred to as the "big four" in terms of voice solutions. It's a euphemism anyway because not everyone is aware that Facebook has devices with a voice interface at all.

Marcin Lewek
Marcin Lewek
Voice