Fundamentals of ML and AI Flashcards
What are Neutral Networks
Neural networks have lots of tiny units called nodes that are connected together. These nodes are organized into layers. The layers include an input layer, one or more hidden layers, and an output layer.
Computer vision
Computer vision is a field of artificial intelligence that makes it possible for computers to interpret and understand digital images and videos.
Natural Language Processing
Natural language processing (NLP) is a branch of artificial intelligence that deals with the interaction between computers and human languages. NLP includes tasks such as text classification, sentiment analysis, machine translation, and language generation.
Diffusion models
-Make new data by making controlled changes to initial sample
-Diffusion is a deep learning architecture system that starts with pure noise or random data.
-Model adds 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 models learn through a two-step process of forward diffusion and reverse diffusion.
-Not a type of transformer model
Forward diffusion
Using forward diffusion, the system gradually introduces a small amount of noise to an input image until only the noise is left over.
Reverse diffusion
In the subsequent reverse diffusion step, the noisy image is gradually introduced to denoising until a new image is generated
Multimodal models
multimodal models can process and generate multiple modes of data simultaneously. For example, a multimodal model could take in an image and some text as input, and then generate a new image and a caption describing it as output. Use cases: automating video captioning, creating graphics from text instructions, answering questions more intelligently by combining text and visual info, and even translating content while keeping relevant visuals.
Generative adversarial networks (GANs0
GANs are a type of generative model that involves two neural networks competing against each other in a zero-sum game framework. 2 types Generator (generates new synthetic data (for example, images, text, or audio) by taking random noise as input and transforming it into data that resembles the training data distribution) and Discriminator (takes real data from the training set and synthetic data generated by the generator as input. Its goal is to distinguish between the real and generated data.)
Large Language models
Takes real data from the training set and synthetic data generated by the generator as input. Its goal is to distinguish between the real and generated data. Includes tokens and vectors
Variational Autoencoders (VAEs)
VAEs are a type of generative model that combines ideas from autoencoders (a type of neural network) and variational inference (a technique from Bayesian statistics). In a VAE, the model consists of two parts, and follows a probability distribution
Encoder: This neural network takes the input data (for example, an image) and maps it to a lower-dimensional latent space, which captures the essential features of the data.
Decoder: This neural network takes the latent representation from the encoder and generates a reconstruction of the original input data.
Reinforcement learning from human feedback (RLHF)
provides human feedback data, resulting in a model that is better aligned with human preferences.
Instruction fine-tuning
uses examples of how the model should respond to a specific instruction. Prompt tuning is a type of instruction fine-tuning.
Retrieval-augmented generation (RAG)
a technique that supplies domain-relevant data as context to produce responses based on that data. 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. RAG will not change the weights of the foundation model, whereas fine-tuning will change model weights.
FM (Foundational Model) Lifecycle
The foundation model lifecycle is a comprehensive process that involves
1. Data selection
2. pre-training
3. optimization
4. evaluation
5. deployment
6. feedback and continuous improvement
Amazon SageMaker
With SageMaker, you can build, train, and deploy ML models for any use case with fully managed infrastructure, tools, and workflows. SageMaker provides all the components used for ML in a single toolset,
Amazon Comprehend
Amazon Comprehend uses ML and natural language processing (NLP) to help you uncover the insights and relationships in your unstructured data. This service performs the following functions:
Identifies the language of the text Extracts key phrases, places, people, brands, or events Understands how positive or negative the text is Analyzes text using tokenization and parts of speech And automatically organizes a collection of text files by topic