who am I
who are You
is this a course for You ?
credits (2 ECTS for >75% attendance, +1 for referat/Congress contribution, +2 Hausarbeit)
Leistungsnachweis
signature-related issues
Feedback box
Congress
1. What did You learn ?
2. What did You like ?
3. What did disturb You?
4. What did You not like ?
and throw it into Feedbackbox.TAKEN Chapter 3 (Babies' Invisible Knowledge) and 4 (The birth of a brain) from Dehaene's "How we Learn"
TAKEN Chapter 5 (Nurture's Share) and 6 (Recycle Your Brain) from Dehaene's "How we Learn"
Chapter 7 (Attention) and 8 (Active Engagement) from Dehaene's "How we Learn"
Chapter 9 (Error Feedback) and 10 (Consolidation) from Dehaene's "How we Learn"
AI unplugged activity - Classification with Decision Trees
AI unplugged activity - #deeplearning
AI unplugged activity - Reinforcement learning
Non-human learning (plants, animals etc.)
Un-learning & "altered" learning.
What did You learn today ?
What was the most important thing You learned this year ?
No direct guidance :: Learner L must identify patterns or relationships from raw input on her own.
Pattern discovery :: Observation often involves recognizing and understanding patterns in the environment, which mirrors what happens in unsupervised learning.
Learning from the environment :: L derives insights from the world or data without external labels or supervision.
What is Your most favorite game / way of playing ?
Any game You would like to bring & play with Your colleagues during the Congress ?
Q-learning is a model-free reinforcement learning algorithm that enables an agent to learn an optimal policy for decision-making. It works by estimating the Q-values (action-value function), which represent the expected cumulative reward for taking an action in a given state and following the best future actions. The agent updates Q-values iteratively using the formula:
