You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"description": "When we use supervised machine learning techniques we need to specify\nthe number of parameters that our model will need to represent the\ndata (number of clusters, number of Gaussians, etc.).\n\nSomewhat, we are making our model inflexible. In this talk we will\nstudy the nonparametric models, in specific, Bayesian Nonparametric\nModels (BNP) whose main purpose is getting more flexible models since\nthat in BNP the parameters can be automatically inferred by the\nmodel.\n\nThe outline is the next:\n\n- Parametric vs Nonparametric models\n- A review on probability distributions\n- Non-parametric Bayesian Methods\n- Dirichlet Process\n- Python (and R maybe) libraries for NPB\n- Conclusions",