All Categories
Artificial Intelligence
Explore questions in the Artificial Intelligence category that you can ask Spark.E!
- Weights and biases are examples of hyperparameters in a neural network.
- The __ test is a widely used test to determine whether a computer exhibits intelligent behavior.
- Deep learning systems _ solve complex problems with a data set that is diverse and __.
- Convolutional neural networks can be used to create deepfakes ranging from image manipulation to news embellishments.
- ______ is the ability of information systems to work with text the way that humans do.
- Experts consider misusing military robots, autonomous attack drones, tricking facing recognition systems, and data poisoning high concern AI-enabled crimes.
- A hyperparameter in a neural network consists of software that has one or more weighted input connections, a bias function, and activation function, and one or more output connections.
- Sephora Virtual Artist is the augmented reality tool that allows customers to try on thousands of makeup products.
- Transferring domain expertise from human experts to the expert system can be difficult because humans cannot always explain how they know what they know.
- Data shift is a machine learning bias that comes from a mismatch between the data used to train and test the system and the data the system actually encounters in the real world.
- _____ is the practice of combining computer code from multiple contributors on a single software project.
- H&R Block uses ____ to understand context, interpret client intent, and draw connections between client statements and relevant areas of their returns.
- The activation rate in a neural network is how much the system is allowed to change the parameters after each training iteration.
- If a computer can perform a useful and specific function that once required human intelligence to perform and does so at human levels or better, this is considered strong AI.
- Experts are moderately concerned with data poisoning.
- BlackSwan is an AI company whose product, Element, integrates _____ to address data acquisition, insight discovery, and predictions.
- Machine learning is a subset of deep learning.
- Fraud detection is an example of _____ classification.
- Deep learning systems do not need to be exposed to labeled historical or training data.
- Classification refers to a predictive modeling problem in which the system generates a class label for a given set of input data.