Elements of AI - Building AI

1. Getting Started With AI

• - Exercise 1: Listing pineapple routes
• - Exercise 2: Pineapple route emissions
• - Exercise 3: Reach the highest summit
• - Exercise 4: Probabilities
• - Exercise 5: Warm-up Temperature
• - Exercise 6: Simulated Annealing

2. Dealing with uncertainty

• - Exercise 7: Flip the coin
• - Exercise 8: Fishing in the Nordics
• - Exercise 9: Block or not
• - Exercise 10: Naive Bayes classifier

3. Machine learning

• - Exercise 11: Real estate price prediction
• - Exercise 12: Least squares
• - Exercise 13: Predictions with more data
• - Exercise 14: Training data vs test data
• - Exercise 15: Vector distances
• - Exercise 16: Nearest neighbor
• - Exercise 17: Bag of words
• - Exercise 18: TF-IDF
• - Exercise 19: looking out for overfitting

4. Neural nerworks

• - Exercise 20: Logistic regression
• - Exercise 21: Neural networks

5. Conclusion

6. Notes

When talking about neural networks, we use slightly different terminology. Instead of coefficients we say weights. The non-linear part of the model, which in the case of logistic regression was the sigmoid function, is called the activation function. One such model is called a neuron. The neurons are connected to each other by letting the output of one neuron be an input of another.

-- https://buildingai.elementsofai.com/Neural-Networks/from-logistic-regression-to-neural-networks