34. SUPERVISED LEARNING
Create predictive model based on a set of features
and labels.
How you would classify each
entry.
Example: Predicting the price of a house
Price
35. SUPERVISED LEARNING
Create predictive model based on a set of features
and labels.
How you would classify each
entry.
Example: Predicting the price of a house
Price
Characteristics of the entries
in your dataset.
Number of rooms, floors,
location, type of property, ...
36. SUPERVISED LEARNING
Create predictive model based on a set of features
and labels.
How you would classify each
entry.
Example: Predicting the price of a house
Price
Characteristics of the entries
in your dataset.
Number of rooms, floors,
location, type of property, ...
Mathematical representation of
the outcome of your training.
Function that takes features
as parameters and is able to
predict a label as output.
37. The ability to create predictions based only on a set of
features.
UNSUPERVISED LEARNING
38. The ability to create predictions based only on a set
of features.
UNSUPERVISED LEARNING
44. WHAT CAN YOU DO
Import an existing,
pre-trained model.
45. WHAT CAN YOU DO
Import an existing,
pre-trained model.
Re-train an imported
model (transfer learning)
46. WHAT CAN YOU DO
Import an existing,
pre-trained model.
Re-train an imported
model (transfer learning)
Define, train and run models
entirely in the browser.
57. LIMITS
● Need large amount of data (except if using pre-trained model).
● Can take a lot of time to train your own model.
58. LIMITS
● Need large amount of data (except if using pre-trained model).
● Can take a lot of time to train your own model.
● Think about the mobile experience.
59. LIMITS
● Need large amount of data (except if using pre-trained model).
● Can take a lot of time to train your own model.
● Think about the mobile experience.
● Liability (some models are black boxes).
60. LIMITS
● Need large amount of data (except if using pre-trained model).
● Can take a lot of time to train your own model.
● Think about the mobile experience.
● Liability (some models are black boxes).
● Bias / ethics.