Review of book On Intelligence
Introduction
In this book, Hawkins develops a theory of how the human brain works. According to his theory, the brain is not a computer, but a memory system that stores experiences in a way that reflects the true structure of the world, remembering sequences of events and their relationships and making predictions based on those memories. Hawkins argues that it is this memory-prediction system that forms the basis of intelligence. The proposed theory is what Hawkins believes the way we can build intelligent machines.
Chapter 3 The Human Brain
In this chapter, Hawkins tells us that we should focus our attention on neocortex. He believes that almost everything about intelligence occurs here. Humans are smarter because our cortex covers a larger area, not because it contains some special class of “smart” cells. In the cortex, lower areas feed information up to higher areas by way of a certain neural pattern of connectivity, while higher areas send feedback down to lower areas using a different connection pattern.
There is a single powerful algorithm implemented by every region of cortex. The inputs to our cortex are all basically alike. All the information that enters our mind comes in as spatial and temporal patterns on the axons.
As long as we can build a system with neocortical algorithm and a science of patterns, we will be able to achieve intelligent.
Chapter 4 Memory
A brain can be faster and more powerful than our fastest digital computers because brain doesn’t “compute” the answers to problem; it retrieves the answers from memory. The answers were stored in memory a long time ago. The entire cortex is a memory system.
There are four attributes of neocortical memory that are fundamentally different from computer memory:
The neocortex stores sequences of patterns.
The neocortex recalls patterns auto-associatively.
The neocortex stores patterns in an invariant form.
The neocortex stores pattern in a hierarchy.
Chapter 5 A New Framework of Intelligence
Our brains use stored memories to constantly make predictions about everything we see, feel, and hear. What we perceive is a combination of what we sense and of our brains’ memory-derived predictions. Prediction is the primary function of the neocortex, and the foundation of intelligence.
The human brain is more intelligent than that of other animals because it can make predictions about more abstract kinds of patterns and longer temporal pattern sequences.
The human cortex is constantly predicting what we will see, hear, and feel. These predictions, when combined with sensory input, are our perceptions. This view of the brain is what Hawkins called the memory-prediction framework of intelligence.
Chapter 6 How the Cortex Works
In this chapter, Hawkins provides a new depiction of the cortical hierarchy where we can say each and every region of cortex forms invariant representations. All regions of cortex from invariant representations of the world underneath them in the hierarchy.
One of the most important concepts in this book is that the cortex’s hierarchical structure stores a model the hierarchical structure or the real world. The real world’s nested structure is mirrored by the nested structure of our cortex.
Learning sequences is the most basic ingredient for forming invariant representations of real-world objects. The memory of sequences allows you not only to resolve ambiguity in the current input, but also to predict which input should happen next.
When we think about the world, we are recalling sequences of patterns that correspond to the way the objects in the world are and how they behave, not how they appear through any particular sense at any point in time.
Thoughts
Overall, the book is a great read. Hawkins describes a new view of looking at human intelligence. The framework he proposed is excellent. But obviously there is still a gap between Hawkins’s brilliant theory and our current AI systems. It would be exciting to see his theories turn into practical intelligent machines.
