1.1 Basic building blocks

• Variables: assignable memory \(\pi = 3.1415926\)
• Operators: modify and combine variables \(+, -, \times, \div, \sqrt{\ \ }\)
• Logic function: comparison of variables \(\lt, \le, =, \ne, \ge, \gt\)
• Functions: process the input to calculate a corresponding output \(y=sin(x)\)
• Input / Output: receiving and sending information to the world (via multimedia)

1.2 Process controls

x = 0
while (x < 5) {
  try(x)
  x += 1
}

x = 0
unless (x > 5) {
  try(x) "
  x += 1
}

if(x == 5) {
   print "smiling"
} else {
   print "frown"
}

unless (x == 5) {
   print "smiling"
} else {
   print "smiling"
}

1.3 Actions

The programmer must …

• specify the actions and nature of every actor.
• determine what conditions must be tested and the appropriate response
• arrange the output.

Examples

• Robot simulator: Path tracing
• Cartoon movie : Wizard vs Ogre

1.3.1 Basic Actors of this Program

3 Sprite objects on a backdrop

1.3.2 Actions of the Wizard

1.3.3 Actions of the Bolt of Lightning

1.3.4 Actions of the Ogre

1.3.5 Actions of the Wizard

1.4 Contrast to AI development

2.1 Regression analysis and modelling

2.2 Analysis

2.3 Cone of Certainty

\[ mpg = 15.103654 - 0.224609 t + 0.006171 t^2\]

2.4 Regression to forecast

2.5 Regression analysis of a data trend

3.1 Combination and crossover

3.1.1 Genetic mutation

3.2 Searching for solutions in complicated domain space

• Most searchs are basically hill-climbing exercises to find the maximum value
• Basically the search creates an ascent path until the peak is found
• However, multiple peaks and valleys can hide the true solution
• Genetic can search multiple areas simultaneously to discover the answer faster.

3.3 A multipeak problem

3.3.1 Mastermind

4.1 Markov Chains

5.1 Digital Neuron

5.2 NeuralNet

5.3 Network Learning

6.1 SOM Examples

6.2 Usefulness of SOM

• Self-learning algorithm
• Clusters data into useful groups
• Compares new data to the nearest groups
• Useful for an initial analysis of unprocessed data
• Attempts to group items by similarity

7.1 Grammerly corrected

Eye halve a spelling checker It came with my pea sea. It marks four my revue miss steaks eye kin knot sea. Eye strike a quay and type a word and weight for it to say Weather eye yam wrong oar write. It shows me straight a weight as soon as a mist ache is made. It nose bee fore two long and eye can put the error rite. It’s rare lea ever wrong. Eye have run this poem threw it, I shore your pleased to no. Its letter is perfect awl the way. My checker told me to sew.

7.2 MS Word corrected

Eyes halve a spelling checker It came with my pea sea. It plainly marks four my revue misses steaks eye kin knot sea. Eye strike a quay and type a word and weight for it to say Weather eye yam wrong or write. It shows me straight a weigh as soon as a mist ache is a maid. It noses bee fore two long and eye can put the error rite. It’s rare lea ever wrong. Eye have run this poem threw it, I shore your pleased to no. Its letter is perfect all the way. My checker told me to sew.

7.3 Manual proof-copy

I have a spelling checker It came with my PC. It plainly marks for my review mistakes I cannot see. I strike a key and type a word and wait for it to say whether I am wrong or right. It shows me straight away as soon as a mistake is made. It knows before too long and I can put the error right. It’s rarely ever wrong. I have run this poem threw it, I am sure you’re pleased to know it’s letter perfect all the way. My checker told me so.

7.4 Results

8.1 State of the art

8.2 Detection avoidance