Exercises Set 1

Question 1

How does machine learning relate to scientific inquiry loop?

Answer 1

Through machine learning we evaluate plausability of our beliefs on hypotheses given observations (data) via Baye's rule.

Question 2

Give the setups for supervised, unsupervised and reinforcement learning problems.

Answer 2

Supervised learning setup: given data set $D=\{(x_1, t_1), \ldots, (x_N, t_N) \}$, infer $p(t|x)$. Unsupervised learning setup: given data set $D=\{x_1, \ldots, x_N \} $, infer $p(x)$. Reinforcement learning setup: let $s_t \in S$ be environmental states, $a_t \in A$ be actions and $r_t \colon A \times S \to [0,1]$ be a reward function. Reinforcement objective is to; $$ \begin{align*} \underset{a_t}{\text{maximize}}& &r_t \end{align*} $$