Zebras can run at up to 40 miles an hour on their long legs. The family groups stick together and will defend a member that is being attacked, look after ill members of the family or search when one goes missing! Zebras often congregrate in very large herds (as big as tens of thousands when migrating across the Serengeti plains) but will still keep to their family groups with the herd. They live in family groups of 5-20 animals, usually made up of one stallion, a few mares and their young. Most zebras live in grasslands and savannas, or in sub-desert.Įvery zebra has a unique pattern of black and white stripes, which work as an excellent camouflage for the animals. ![]() Zebras are medium-sized members of the horse family, native to southern and central Africa. Based on the training data, the SVM separates the "space" of all possible fish into two parts, which correspond to the classes we are trying to learn (such as "blue" or "not blue").31st January each year is International Zebra Day - the perfect excuse to learn about zebras and explore our collection of zebra resources below! Try some of our printable activities or have a go at a zebra craft ot two with the kids. ![]() We look at each component of the fish (such as eyes, mouth, body) and assemble all of the metadata for the components (such as number of teeth, body shape) into a vector of numbers for each fish. Levels 6-8 use a Support-Vector Machine (SVM). We classify the new image with the same label (such as "fish" or "not fish") as the images from the training set with the most similar results. Then, for a new image, we feed it to MobileNet and compare its resulting list of annotations to those from the training dataset. Each image in the training dataset is fed to MobileNet, as pixels, to obtain a list of annotations that are most likely to apply to it. In order to customize this model with the labeled training data the student generates in this activity, we use a technique called Transfer Learning. A MobileNet model is a convolutional neural network that has been trained on ImageNet, a dataset of over 14 million images hand-annotated with words such as "balloon" or "strawberry". Levels 2-4 use a pretrained model provided by the TensorFlow MobileNet project. Train a machine learning model with text, numbers, or images, and use it to make games in Scratch.Ī new alternate curriculum unit for the Exploring Computer Science (ECS) curriculum.Ī series of free online courses created by Reaktor and the University of Helsinki.Īn AI education platform for building games, programming robots and training. Help protect the endangered Cape Mountain Zebra by identifying the different animals in the images.Īccess free resources including a lesson plan, videos, computer science curriculum, and teacher trainings. Start exploring machine learning through pictures, drawings, language, music, and more. ![]() ![]() Train a computer to recognize your own images, sounds, and poses. A free app that narrates the world around you in a variety of languages.Ĭan a neural network learn to recognize doodling?
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |