zeroshotlearning.ai

#Zero Shot Learning AI Meta

#Zero Shot Learning (ZSL) | Allowing systems to identify and categorize new items without needing any prior examples

#Zero shot object detection | System can recognize objects based on their descriptive features instead of depending on labeled data

#Visual Intelligence Platform

#Generalized Zero Shot Learning (GSZL) | Recognizing new classes only by examining their descriptions | Helping AI systems swiftly process new data in real-world circumstances, making them more scalable

#Visual Data Management

#SLAM | Simultaneous Localization and Mapping

#Robotic Perception | Acquiring knowledge from sensor data

#Small Object Detection

#Convnet Based Object Detection

#Deep Learning For Object Detection

#Moving Object Trajectory Prediction

#Ship Detection

#Ship Classification

#Neural Network For Object Detection

#Fast Object Detection

#Road Crack Detection

#Object Detection For Avoidance

#Generic Object Detection

#Surface Object Detection

#Moving Object Detection

#Situations where getting labeled data is hard

#Studying rare diseases

#Studying newly discovered species

#Language processing

#Letting machines adapt quickly without tons of extra training

#Computational biology

#Machine learning models requiring zero examples (shots) of class they need to recognize

#Semantic Embedding Space | Representing both seen and unseen classes in common space | Word vectors | Semantic descriptions

#Training model on seen classes, incorporating relationships with unseen classes

#Inferencing by relating unseen class to semantic embedding space and predicting class based on its relationship to seen classes

#Recognizing unseen

#Understanding specific visual patterns

#Predicting classes without ever having seen images during training

#Allowing models to make predictions without needing examples of every class

#Ambiguity in Unseen Classes | Handling unseen classes that may be similar to multiple seen classes

#Creating machines that learn more like humans

#Developing more flexible and resource-efficient models

#Synthetic data generation (SDG)

#Model training

#Spatial-temporal graph convolutional network (ST-GCN)

#Programming new actions for robots

#Position and orientation randomization for characters, agents, and objects

#Generating synthetic data on human characters and robots

#Creating action recognition model

#Simulating and validating robots, for multiple domains

#Creating diverse scenes

#Recognizing range of actions across different scenarios

#Action Recognition Model

#Field Foundation Model (FFMs) | Physical world model using sensor data as an input | Field AI robots can understand how to move in world, rather than just where to move | Very heavy probabilistic modeling | World modeling becomes by-product of Field AI.robots operating in the world rather than prerequisite for that operation | Aim is to just deploy robot, with no training time needed | Autonomous robotic systems applucations | Field AI is software company making sensor payloads that integrate with their autonomy software | Autonomous humanoid Field AI can do | Focus on platforms that are more affordable | Integrating mobility with high-level planning, decision making, and mission execution | Potential to take advantage of relatively inexpensive robots is what is going to make the biggest difference toward Field AI commercial success

#Large Language Model (LLM) | Foundational LLM: ex Wikipedia in all its languages fed to LLM one word at a time | LLM is trained to predict the next word most likely to appear in that context | LLM intellugence is based on its ability to predict what comes next in a sentence | LLMs are amazing artifacts, containing a model of all of language, on a scale no human could conceive or visualize | LLMs do not apply any value to information, or truthfulness of sentences and paragraphs they have learned to produce | LLMs are powerful pattern-matching machines but lack human-like understanding, common sense, or ethical reasoning | LLMs produce merely a statistically probable sequence of words based on their training | LLMs are very good at summarizing | Inappropriate use of LLMs as search engines has produced lots of unhappy results | LLM output follows path of most likely words and assembles them into sentences | Pathological liars as a source for information | Incredibly good at turning pre-existing information into words | Give them facts and let them explain or impart them

#Retrieval Augmented Generation. (RAG LLM) | Designed for answering queries in a specific subject, for example, how to operate a particular appliance, tool, or type of machinery | LLM takes as much textual information about subject, user manuals and then pre-process it into small chunks containing few specific facts | When user asks question, software system identifies chunk of text which is most likely to contain answer | Question and answer are then fed to LLM, which generates human-language answer in response to query | Enforcing factualness on LLMs