AWS AI Practitioner Flashcards
Portion of training training data is labeled and feedback is provided in the form of rewards or penalties. What type of learning
Reinforcement learning
What are the two types of inferencing?
Batch and Real time
Deep learning is used in which use 2 cases?
Computer vision and NLP
What are FMs in generative AI?
Pretrained models
Are FMs pre trained using reinforced learning? True or False?
False. FMs are typically pre-trained through self-supervised learning
Self-supervised learning makes use of the structure within the data to autogenerate labels. True or False?
True
Optimization of pre trained FMs are done using what?
Prompt engineering,
Retrieval-augmented generation (RAG),
Fine-tuning on task-specific data
LLMs, Diffusion and Multiodel models are what?
This is and FM model
Thease are numerical representations of tokens, where each token is assigned a vector (a list of numbers) that captures its meaning and relationships with other tokens?
Embeddings
Which is the models which gradually add more and more meaningful information to this noise until they end up with a clear and coherent output, like an image or a piece of text?
Diffusion model
Which model has generator and discriminator?
Generative adversarial networks
Which model has encoders and decoders?
Varional autoencoders
What are the components of prompt engineering
Instructions, Context, Input data and Output indicator
What is a supervised learning process that involves taking a pre-trained model and adding specific, smaller datasets?
Fine tuning
Two types of fine tuning
Instruction fine-tuning and Reinforcement learning from human feedback (RLHF)
Fine tuning does it add weight to the data?
Yes
What is Retrieval-augmented generation (RAG)?
Supplies domain-relevant data as context to produce responses based on that data.
How is RAG different from fine tuning
Rather than having to fine-tune an FM with a small set of labeled examples, RAG retrieves a small set of relevant documents and uses that to provide context to answer the user prompt
What are two types of supervised learning?
Classification and Regression
Predicting continuous or numerical values based on one or more input variable?
Regression
Forcasting uses which supervised learning technique?
Regression
Diagnostic uses which supervised learning technique?
Classfication
What are two types of unsupervised learning?
Clustering and Dimensionality reduction
Grouping of unstructured data is done in which type of unsupervised learning?
Clustering
Reducing the number of features or dimensions in a dataset in which type of unsupervised learning?
Dimensionality reduction
Which learning type continuously improves its model by mining feedback from previous iterations?
Reinforcement learning
In which learning the reward of a desired outcome is known, but the path to achieving it isn’t?
Reinforcement learning
How to reduce toxity risk in generative AI?
Use guardrail models
What does guradrail models do?
These models will detect and filter out unwanted content
What is the risk term for when model generates inaccurate responses that are not consistent with the training data?
Hellucinations
What is the risk term when model might generate different outputs for the same input?
Nondeterminism
What is the risk term when the information shared with your model can include personal information and can potentially violate privacy laws?
Data security and privacy concerns
What is the risk term when output generated by model has PII?
Regulatory violations
Which generative AI model used for chatbots?
Llama
Which generative AI model used for code generation?
Claude
Which generative AI model used for code gaming?
Stable Diffusion
Which generative AI has embeddings?
Amazon Titan
Which generative AI has a use case of Healthcare – summarize key ideas from long text?
Command
What are the capabilities of generative AI?
SPARCD
Adaptability
Responsiveness
Simplicity
Creativity and exploration
Data efficiency
Personalization
Recommendation engines, gaming, and voice assistance are examples of which type of AI system?
Traditional AI
Chatbots, code generation, and text and image generation are examples of which type of AI system?
Generative AI
When is a model is underfitted?
When a model has a high bias
Overfitting happens when?
When model performs well on the training data but does not perform well on the evaluation data
