Chapter 1 An Informal Introduction ‣ Learning Deep Representations of Data Distributions

“Just as the constant increase of entropy is the basic law of the universe, so it is the basic law of life to be ever more highly structured and to struggle against entropy.”   – Václav Havel The world we inhabit is neither fully random nor completely unpredictable.1 Instead, it follows certain orders, patterns, and laws that render it largely predictable.2 The very emergence and persistence of life depend on this predictability. Only by learning and memorizing what is predictable in the environment can life survive and thrive, since sound decisions and actions hinge on reliable predictions. Because the world offers seemingly unlimited predictable phenomena, intelligent beings—animals and humans—have evolved ever more acute senses: vision, hearing, touch, taste, and smell. These senses harvest high-throughput sensory data to perceive environmental regularities. Hence, a fundamental task for all intelligent beings is to learn and memorize predictable information from massive amounts of

1 An Informal Introduction to Intelligence In this chapter Chapter 1: An Informal Introduction to Intelligence 1.1: Intelligence, Cybernetics, and Artificial Intelligence 1.2: What to Learn? 1.3: How to Learn? 1.4: A Unifying Approach 1.5: Bridging Theory and Practice for Machine Intelligence Chapter 1 An Informal Introduction to Intelligence “ Just as the constant increase of entropy is the basic law of the universe, so it is the basic law of life to be ever more highly structured and to struggle against entropy. ” \(~\) – Václav Havel 1.1 Intelligence, Cybernetics, and Artificial Intelligenc

saved by

• Ali Ahmad

related reading

• 9 Open Problems and Directions about Intelligencema-lab-berkeley.github.io
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• pdfopenreview.net
• The Little Book of Deep Learningfleuret.org
• GenAI Handbookgenai-handbook.github.io
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Juergen Schmidhuber's home page - Universal Artificial Intelligence - AI - Deep Learning - Recurrent Neural Networks - Computer Vision - Object Detection - Image segmentation - GANs - Transformers with linearized self-attention - Goedel Macpeople.idsia.ch
• deeplearningbook.org/contents/ml.htmldeeplearningbook.org
• Intelligence as efficient model building | Alex’s blogatelfo.github.io
• Researchbactra.org
• Theoretical Motivations for Deep Learning | Rinu Boneyrinuboney.github.io
• Building machines that learn and think like people | Behavioral and Brain Sciences | Cambridge Corecambridge.org