Google Cloud Skills Boost Flashcards
What is Generative AI?
It is a type of Artificial Intelligence technology, that can produce various types of content, including: text, imagery, audio and synthetic data.
It is a subset of Deep Learning, which means:
1. Uses ANN.
2. Can be supervised, unsupervised and semi-supervised.
What is Artificial Intelligence?
It is the theory and development of computer systems able to perform tasks normally requiring human intelligence.
What is Machine Learning?
It is a subfield of AI, in which a program or system trains a model from input data. ML gives computers the ability to learn without explicit programming.
What is Deep Learning?
It is a type of ML, that uses Artificial Neural Networks.
What is a prompt in LLM context?
It is the input given to a model (question in ChatGPT)
What is a Foundation Model?
It is a large AI model pre-trained on a vast quantity of data, designed to be adapted or fine tuned to a wide range of downstream tasks, such as sentiment analysis, image captioning, object recognition, etc.
These models have the potential to revolutionize many industries.
What are Large Language Models?
These are:
- Large –> train DS and parameters.
- General-purpose
- Pre-trained
- Fine-tuned for specific purposes
Benefits of using LLM?
- Single model can be used for different tasks.
- Fine-tuned process requires minimal data.
- The performance is continuously growing with more data and parameters.
Image Generation Model Families - Variational Autoencoders?
Encode images to a compressed size, then decode back to the original size, while learning the distribution of the data.
Image Generation Model Families - Generative Adversarial Models?
Pit two neural networks against each other. One NN, the generator creates images, and the other, the discriminator, predicts if the image is reao or fake. Over time, the discriminator gets better and better at distiguishing between real and fake and the generator gets better at creating real looking fakes.
Image Generation Model Families - Autoregressive Models?
Generates images by treating an image as a sequence of pixels.
Image Generation Model Families - Difussion Models?
The essential idea is to systematically and slowly destroy structure in a data distribution through an iterative forward diffusion process. We then learn a reverse diffusion process that restores structure in data, yielding a highly flexible and tractable generative model of the data.
