Which of the following are True? (Check all that apply). You also know that human-level error on the road sign and traffic signals classification task is around 0.5%.
The pedestrian multiple choice quiz answers download#
The distribution of data you care about contains images from your car’s front-facing camera which comes from a different distribution than the images you were able to find and download off the internet. True/False?Īs seen in the lecture on multi-task learning, you can compute the cost such that it is not influenced by the fact that some entries haven’t been labeled. If one example is equal to then the learning algorithm will not be able to use that example. For example, y(i) = means the image contains a stop sign and a red traffic light.īecause this is a multi-task learning problem, you need to have all your y(i) vectors fully labeled. 900,000 labeled images of roads downloaded from the internet.Įach image’s labels precisely indicate the presence of any specific road signs and traffic signals or combinations of them.100,000 labeled images taken using the front-facing camera of your car.10,000 images on which the algorithm made a mistakeĪfter working on the data for several weeks, your team ends up with the following data:.500 images on which the algorithm made a mistake.Which of these datasets do you think you should manually go through and carefully examine, one image at a time? You are carrying out error analysis and counting up what errors the algorithm makes. Softmax would be a good choice if one and only one of the possibilities (stop sign, speed bump, pedestrian crossing, green light and red light) was present in each image. You plan to use a deep neural network with ReLU units in the hidden layers.įor the output layer, a softmax activation would be a good choice for the output layer because this is a multi-task learning problem. The goal is to recognize which of these objects appear in each image. Your goal is to detect road signs (stop sign, pedestrian crossing sign, construction ahead sign) and traffic signals (red and green lights) in images. If you train a basic model and carry out error analysis (see what mistakes it makes) it will help point you in more promising directions. Spend a few days training a basic model and see what mistakes it makes.Īs discussed in lecture, applied ML is a highly iterative process.What is the first thing you do? Assume each of the steps below would take about an equal amount of time (a few days). You are just getting started on this project.
Week 2 Quiz - Autonomous driving (case study)
0 kommentar(er)
