Here is the link… Jump to fastai/fastbook lecture 01
1.Do you need these for deep learning?
- Lots of math T / F ➔ F
- Lots of data T / F ➔ F
- Lots of expensive computers T / F ➔ F
- A PhD T / F ➔ F
2. Name five areas where deep learning is now the best in the world.
: NLP, Computer Vision, Medicine, Biology, Image generation, Recommendation systems, Playing games, Robotics …etc.
3. What was the name of the first device that was based on the principle of the artificial neuron?
: Perceptrons
4. Based on the book of the same name, what are the requirements for parallel distributed processing (PDP)?
(1)a set of rocessing units
(2)A state of activation
(3)An output function for each unit
(4)A pattern of connectivity among units
(5)A propagation rule for propagating patterns of activities through the network of connectivities
(6)An activation rule for combining the inputs impinging on a unit with the current state of that unit to produce an output for the unit
(7)An environment within which the system must operate
5. What were the two theoretical misunderstandings that held back the field of neural networks?
(1) adding just one extra layer of neurons was enough
(2) to get good performance, you need to use even more layers of neurons
6. What is a GPU?
:GPU is also known as a graphics card. A special kind of processor in your computer that can handle thousands of single tasks at the same time, especially designed for displaying 3D environments on a computer for playing games. These same basic tasks are very similar to what neural networks do, such that GPUs can run neural networks hundreds of times faster than regular CPUs. All modern computers contain a GPU, but few contain the right kind of GPU necessary for deep learning.
7. Open a notebook and execute a cell containing: 1+1
. What happens?
➔ 2
8. Follow through each cell of the stripped version of the notebook for this chapter. Before executing each cell, guess what will happen.
➔ okidoki
9. Complete the Jupyter Notebook online appendix.
➔ okidoki
10. Why is it hard to use a traditional computer program to recognize images in a photo?
It was hard that adding just one extra layer of neurons was enough to allow any mathematical function to be approximated with these neural networks, but in practice such networks were often too big and too slow to be useful. Also, you need to use even more layers of neurons to get practical good performance.
11. What did Samuel mean by “weight assignment”?
Weights are just variables, and a weight assignment is a particular choice of ‘s values for those variables. The program’s inputs are values that it processes in order to produce its results. The program’s weight assignments are other values that define how the program will operate.
12. What term do we normally use in deep learning for what Samuel called “weights”?
They are most normally referred to as model parameters these days. The term weights is reserved for a particular type of model parameter.
13. Draw a picture that summarizes Samuel’s view of a machine learning model.
16. Why is it hard to understand why a deep learning model makes a particular prediction?
It is hard to do so without enough trust in the models or an efficient procedure to explain unintended behavior, especially considering that the deep neural networks are born as black-boxes.
17. What is the name of the theorem that shows that a neural network can solve any mathematical problem to any level of accuracy?
: mathematical theory of artificial neural networks
18. What do you need in order to train a model?
:Suppose we arrange for some automatic means of testing the effectiveness of any current weight assignment in terms of actual performance and provide a mechanism for altering the weight assignment so as to maximize the performance. So we need inputs, weights for the model.
19. How could a feedback loop impact the rollout of a predictive policing model?
If the model is trained, then the weights as being part of the model, since we’re not varying them anymore.
20. Do we always have to use 224×224-pixel images with the cat recognition model?
This is the standard size for historical reasons. The old models which were pre-trained were in this size. So we need to fix the size when we use old models.
21. What is the difference between classification and regression?
The main difference between them is that the output variable in regression is numerical (or continuous) while that for classification is categorical or discrete. Besides, a classification model is one which attempts to predict a class or category. Otherwise, a regression model is one which attempts to predict one or more numeric quantities such as a temperature or a location.
22. What is a validation set? What is a test set? Why do we need them?
Validation set is the sample of data used to provide an unbiased evaluation of a model fit on the training dataset while tuning model hyperparameters. The evaluation becomes more biased as skill on the validation dataset is incorporated into the model configuration.
Test data set is the sample of data used to provide an unbiased evaluation of a final model fit on the training dataset.
23. What will fastai do if you don’t provide a validation set?
If we don’t have appropriate amount of data then we generate new data based on existing data. This process is called Data augmentation that refers to creating random variations of our input data such that they appear different, but do not actually change the meaning of the data.
