Chapter 1 + 3 Flashcards
Where did the ideas that led to the first programmable computers come from?
Mathematicians’ attempts to understand human thought—particularly logic—as a mechanical process of “symbol manipulation.” Digital computers are essentially symbol manipulators, pushing around combinations of the symbols 0 and 1.
How is intelligence a ‘suitcase word?’
Because its central notion—intelligence—remains so ill-defined. It is packed like a suitcase with a jumble of different meanings. Artificial intelligence inherits this packing problem, sporting different meanings in different contexts.
intelligence can be binary (something is or is not intelligent), on a continuum (one thing is more intelligent than another thing), or multidimensional (someone can have high verbal intelligence but low emotional intelligence).
For better or worse, the field of AI has largely ignored these various distinctions. What has it focused on instead?
Instead, it has focused on two efforts: one scientific and one practical. On the scientific side, AI researchers are investigating the mechanisms of “natural” (that is, biological) intelligence by trying to embed it in computers. On the practical side, AI proponents simply want to create computer programs that perform tasks as well as or better than humans, without worrying about whether these programs are actually thinking in the way humans think.
At the 1956 Dartmouth workshop, different participants espoused divergent opinions about the correct approach to take to develop AI.
Describe three of these opinions
Some people—generally mathematicians—promoted mathematical logic and deductive reasoning as the language of rational thought.
Others championed inductive methods in which programs extract statistics from data and use probabilities to deal with uncertainty.
Still others believed firmly in taking inspiration from biology and psychology to create brain-like programs.
At the 1956 Dartmouth workshop, different participants espoused divergent opinions about the correct approach to take to develop AI.
Describe three of these opinions
Some people—generally mathematicians—promoted mathematical logic and deductive reasoning as the language of rational thought.
Others championed inductive methods in which programs extract statistics from data and use probabilities to deal with uncertainty.
Still others believed firmly in taking inspiration from biology and psychology to create brain-like programs.
How was this disagreement about the correct approach for AI resolved?
Arguments among proponents of these various approaches persist to this day. And each approach has generated its own panoply of principles and techniques, fortified by specialty conferences and journals, with little communication among the subspecialties.
Which family of AI methods has ‘risen above the anarchy to become the dominant AI paradigm’?
One family of AI methods—collectively called deep learning (or deep neural networks).
Which family of AI methods has ‘risen above the anarchy to become the dominant AI paradigm’?
One family of AI methods—collectively called deep learning (or deep neural networks).
How is AI and deep learning not the same thing?
AI is a field that includes a broad set of approaches, with the goal of creating machines with intelligence. Deep learning is only one such approach.
Deep learning is itself one method among many in the field of machine learning, a subfield of AI in which machines “learn” from data or from their own “experiences.”
What philosophical split occurred early in the AI research community?
The split between symbolic and subsymbolic AI. A symbolic AI program’s knowledge consists of words or phrases (the “symbols”), typically understandable to a human, along with rules by which the program can combine and process these symbols in order to perform its assigned task. (e.g general problem solver, similar to how we code: CURRENT STATE:
LEFT-BANK = [3 MISSIONARIES, 3 CANNIBALS, 1 BOAT] RIGHT-BANK = [EMPTY] )
Subsymbolic AI programs do not contain the kind of human-understandable language we saw in the Missionaries and Cannibals example above. Instead, a subsymbolic program is essentially a stack of equations—a thicket of often hard-to-interpret operations on numbers. (
How did these two approaches differ in their view of AI
Advocates of the symbolic approach to AI argued that to attain intelligence in computers, it would not be necessary to build programs that mimic the brain. Instead, the argument goes, general intelligence can be captured entirely by the right kind of symbol-processing program.
Symbolic AI was originally inspired by mathematical logic as well as by the way people described their conscious thought processes. In contrast, subsymbolic approaches to AI took inspiration from neuroscience and sought to capture the sometimes-unconscious thought processes underlying what some have called fast perception, such as recognising faces or identifying spoken words.
How did these two approaches differ in their view of AI
Advocates of the symbolic approach to AI argued that to attain intelligence in computers, it would not be necessary to build programs that mimic the brain. Instead, the argument goes, general intelligence can be captured entirely by the right kind of symbol-processing program.
Symbolic AI was originally inspired by mathematical logic as well as by the way people described their conscious thought processes. In contrast, subsymbolic approaches to AI took inspiration from neuroscience and sought to capture the sometimes-unconscious thought processes underlying what some have called fast perception, such as recognizing faces or identifying spoken words.
At the 1956 Dartmouth workshop, different participants espoused divergent opinions about the correct approach to take to develop AI.
Describe three of these opinions
Some people—generally mathematicians—promoted mathematical logic and deductive reasoning as the language of rational thought.
Others championed inductive methods in which programs extract statistics from data and use probabilities to deal with uncertainty.
Still others believed firmly in taking inspiration from biology and psychology to create brain-like programs.
How was this disagreement about the correct approach for AI resolved?
Arguments among proponents of these various approaches persist to this day. And each approach has generated its own panoply of principles and techniques, fortified by specialty conferences and journals, with little communication among the subspecialties.
Which family of AI methods has ‘risen above the anarchy to become the dominant AI paradigm’?
One family of AI methods—collectively called deep learning (or deep neural networks).
How is AI and deep learning not the same thing?
AI is a field that includes a broad set of approaches, with the goal of creating machines with intelligence. Deep learning is only one such approach.
Deep learning is itself one method among many in the field of machine learning, a subfield of AI in which machines “learn” from data or from their own “experiences.”
What philosophical split occurred early in the AI research community?
The split between symbolic and subsymbolic AI.
A symbolic AI program’s knowledge consists of words or phrases (the “symbols”), typically understandable to a human, along with rules by which the program can combine and process these symbols in order to perform its assigned task.
Subsymbolic AI programs do not contain the kind of human-understandable language we saw in the Missionaries and Cannibals example above. Instead, a subsymbolic program is essentially a stack of equations—a thicket of often hard-to-interpret operations on numbers.
How did these two approaches differ in their view of AI
Advocates of the symbolic approach to AI argued that to attain intelligence in computers, it would not be necessary to build programs that mimic the brain. Instead, the argument goes, general intelligence can be captured entirely by the right kind of symbol-processing program. Agreed, the workings of such a program would be vastly more complex than the Missionaries and Cannibals example, but it would still consist of symbols, combinations of symbols, and rules and operations on symbols.
Symbolic AI was originally inspired by mathematical logic as well as by the way people described their conscious thought processes. In contrast, subsymbolic approaches to AI took inspiration from neuroscience and sought to capture the sometimes-unconscious thought processes underlying what some have called fast perception, such as recognizing faces or identifying spoken words.
Describe an example of symbolic AI
General problem solver (similar to how we code). The creators of the General Problem Solver had recorded several students “thinking out loud” while solving the cannibals and missionaries conundrum and other logic puzzles and programmed to mimic this:
CURRENT STATE:
LEFT-BANK = [3 MISSIONARIES, 3 CANNIBALS, 1 BOAT] RIGHT-BANK = [EMPTY]
DESIRED STATE:
LEFT-BANK = [EMPTY]
RIGHT-BANK = [3 MISSIONARIES, 3 CANNIBALS, 1 BOAT] )
At each step in its procedure, GPS attempts to change its current state to make it more similar to the desired state. In its code, the program has “operators” (in the form of subprograms) that can transform the current state into a new state and “rules” that encode the constraints of the task.
Describe an example of subsymbolic AI
Perceptron was an important milestone in AI and was the influential great-grandparent of modern AI’s most successful tool, deep neural networks. Rosenblatt’s invention of perceptrons was inspired by the way in which neurons process information.
Analogous to the neuron, the perceptron adds up its inputs, and if the resulting sum is equal to or greater than the perceptron’s threshold, the perceptron outputs the value 1 (it “fires”); otherwise it outputs the value 0 (it “does not fire”). E.g recognising the figure ‘8’ through 324 pixels
Unlike the symbolic General Problem Solver system that I described earlier, a perceptron doesn’t have any explicit rules for performing its task; all of its “knowledge” is encoded in the numbers making up its weights and threshold.
But how, exactly, can we determine the correct weights and threshold for a given task?
Rosenblatt proposed a brain-inspired answer: the perceptron should learn these values on its own. Like the behavioral psychology theories popular at the time, Rosenblatt’s idea was that perceptrons should learn via conditioning. Rosenblatt’s idea was that the perceptron should similarly be trained on examples: it should be rewarded when it fires correctly and punished when it errs.
What name is given to this form of conditioning and how does it work - 3
This form of conditioning is now known in AI as supervised learning. During training, the learning system is given an example, it produces an output, and it is then given a “supervision signal,” which tells how much the system’s output differs from the correct output. The system then uses this signal to adjust its weights and threshold.
Supervised learning typically requires a large set of positive examples (for instance, a collection of 8s written by different people) and negative examples (for instance, a collection of other handwritten digits, not including 8s). Some of the positive and negative examples are used to train the system; these are called the training set. The remainder—the test set—is used to evaluate the system’s performance after it has been trained.
Name and describe the algorithm used to carry out this supervised learning
The perceptron-learning algorithm: Initially, the weights and threshold are set to random values between −1 and 1. The first training example is given to the perceptron; at this point, the perceptron doesn’t see the correct category label. The perceptron multiplies each input by its weight, sums up all the results, compares the sum with the threshold, and outputs either 1 or 0. If the perceptron is correct, the weights and threshold don’t change. But if the perceptron is wrong, the weights and threshold are changed a little bit, making the perceptron’s sum on this training example closer to producing the right answer.
Moreover, the amount each weight is changed depends on its associated input value; that is, the blame for the error is meted out depending on which inputs had the most impact. For example, in the 8 of figure 3A, the higher-intensity (here, black) pixels would have the most impact, and the pixels with 0 intensity (here, white) would have no impact. This process then repeats with gradual changes (similar to Skinner) until it settles on a set of weights and threshold values which work for the whole set.
Did symbolic or subsymbolic AI ‘dominate’ the field for the first three decades?
Symbolic AI of the kind illustrated by GPS ended up dominating the field for its first three decades, most notably in the form of expert systems, in which human experts devised rules for computer programs to use in tasks such as medical diagnosis and legal decision-making.
