One open problem in ML is designing interfaces between models. Having a model as part of your application is a challenge. Building a new model that depends on the previous one is even harder. Now you can’t train the first one without retraining the second...
-
-
These are absolutely amazing, thanks for sharing. Loving your twelve truths, in particular 0 and 1, which were particularly apparent in my work at Insight guiding newcomers to the field.
-
Glad you enjoy it. I talk about some of it in our book. Looking forward to reading your upcoming book.https://www.amazon.com/dp/1491978236/ref=cm_sw_r_cp_api_i_tV7hEb2R0BQE5 …
Kraj razgovora
Novi razgovor -
-
-
Guess
@mlpowered question was addressed in pt 5. End to end solutions and pipelined archtectures isn't scalable for use cases in future. We need models to plug in and out much like the microservices world. - Još 1 odgovor
Novi razgovor -
-
-
Thank you for sharing. Love it.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
. Works on: Startups, Natural Language Processing