Automatic Programming
- Automatic Programming Server
- This is an experimental offering of an Automatic Programming Server that will write computer programs for you.
It is currently UNDER CONSTRUCTION. The user interface is not fancy.
You are free to use the programs that are generated for
any legitimate purpose. However, these program...
- Programming and Problem Solving by Connecting Diagrams
- This is a demonstration of the VIP (View Interactive Programming) program. VIP allows the user to create scientific programs or to solve physics problems by connecting diagrams that represent physical and mathematical principles. The following example shows a specification for calculating the mas...
- Graphical Programming Server
-
This is an experimental offering of a Graphical Programming Server (GPS)
that will write computer programs for you.
It is currently UNDER CONSTRUCTION. The user interface is not fancy.
You are free to use the programs ...
Intelligent Robotics
- The Spatial Semantic Hierarchy
- The cognitive map is the body of knowledge a human or robot has
about its large-scale spatial environment. We have developed a computational
theory of the human and robotic cognitive map [Kuipers, 1978, 1982;
Kuipers and Levitt, 1988; Kuipers and Byun, 1988, 1991]. Our theory
of th...
- UT Intelligent Wheelchair Project
- The Intelligent Wheelchair is intended for people with normal
cognitive and perceptual functioning and severe mobility and
communication restrictions. This involves participation from several
other groups in the Artificial Intelligence
Lab in the UT-Austin ...
Knowledge Representation & Reasoning
- Rapid Knowledge Formation
- The goal of the DARPA-funded Rapid Knowledge Formation (RKF) project (1999-2003) was to develop technology that enables people who are untrained in AI to build knowledge bases efficiently and accurately. This goal aligned perfectly with our research agenda, which we're continuing to explore under...
- The Botany Knowledge Base
- The goal of the Botany Knowledge Base (BKB) project was to create a laboratory for research on AI tasks that require extensive knowledge, such as novel problem solving, language understanding, and learning.
The BKB contains fundamental knowledge in the areas of plant physiology, anatomy and d...
- Project Halo
- The goal of Project Halo is to create a Digital Aristotle - a Knowledge System capable of answering hard, novel questions and solving advanced problems in a broad range of scientific disciplines.
Project Halo is sponsored and managed by Vulcan, Inc. Vulcan has a nice website (www.projecthalo....
Learning Agents
- The UT Austin Villa Robot Soccer team
- We are a RoboCup soccer team from the Department of Computer Sciences at the University of Texas at Austin. We compete in both the legged and simulation leagues of RoboCup soccer. Our team name is a play on the name of a prominent English football club, Aston Villa.
- The TacTex supply chain management autonomous trading agent
- Welcome to the home of TacTex, an agent designed for the Supply Chain Management scenario of the Trading Agent Competition (TAC SCM).
- AIM: Autonomous Intersection Management
- This project "AIM"s to create a scalable, safe, and efficient multiagent framework for managing autonomous vehicles at intersections.
Intelligent vehicle technology is progressing very rapidly and recent advances suggest that autonomous vehicle navigation will be possible in the near f...
- Autonomic computing
- Cognitive Systems Research Group Meetings
The Cognitive Systems group will meet on a bi-weekly basis (more or less) at 3:00pm on Tuesdays
Neural Networks
- Self-Organization of Directional Selectivity
- Our goal is to understand how orientation tuning and direction selectivity simultaneously develop in the visual cortex. With this goal in mind we first built a SOM-based model that self-organized to represent these features. We then created a more low-level model, based on a delay adaptation lear...
- PGLISSOM: Perceptual Grouping in a Self-Organizing Map of Spiking Neurons
- Visual perceptual grouping is a process of identifying constituents that together form a group. In this project, a self-organizing map of spiking neurons was developed to understand the neural mechanisms of perceptual grouping. Grouping events were represented by the degree of synchrony among neu...
- Dynamic Resource Allocation on a Multiprocessor Chip
- To obtain best performance in a multi-processor chip, on-chip resources such as cache memory and off-chip bandwidth must be managed dynamically. In this project, ESP is used to evolve neural networks to decide how to continuously reallocate the available cache banks to processors. Trace-based sim...
- Modeling the Emergence of Syllable Systems
- Syllable systems across languages share a number of common patterns. A particularly compelling explanation for these patterns is that they orginate from constraints provided by the perceptual and articulatory systems of language users. In this research, we use genetic algorithms to examine how a ...
- Optimizing a Manufacturing Process
- In many real world optimization problems, such as resource management and manufacturing, the optimization has to be done under uncertainty. Uncertainty makes the task nonlinear, and standard methods such as Linear Programming do not perform very well. In this project, the aim is to evolve neural ...
- Diverse Behavior in Teams of Homogeneous Agents
- Many classes of cooperative multi-agent systems require a diversity of behavior among the agents in order to optimize their performance as a team in the system. Conventionally the control policies for the agents in such systems are programmed or trained so that individual agents are hard-coded to...
- Understanding Complex Sentences with the Sentence Gestalt Model
- The integrated processing-decoding network model of St. John and McClelland (1990) was revised to allow extracting the predicate content of complex sentences directly from an incoming stream of word tokens. The input stream was presented to the network without any syntactic markup such as bracket...
- Cooperative Coevolution of Multi-Agent Systems
- The Enforced Subpopulations (ESP) method can be extended to evolving multiple networks simultaneously, and applied to multi-agent problem solving tasks. In the prey capture domain, multiple predators evolved to perform different and compatible roles, so that the whole team of predators efficie...
- NEAT: Evolving Increasingly Complex Neural Network Topologies
- Many neuroevolution methods evolve fixed-topology
networks.
Some methods evolve topologies in addition to
weights, but these usually have a bound on the complexity of
networks that can be evolved and begin evolution with random topologies.
This project is based on a
neuroevolution metho...
- Real-time Interactive Gaming
- In standard neuro-evolution, the objective is to evolve a network that
best handles a given task. Although this approach is useful for static
tasks, it does not work well in real-time domains where the environment
(and therefore the task) can vary. Furthermore, if the real-time domain
is in...
- Sound System Differentiation Through Time
- The sound structure of language changes over time due to the interaction of socio-cultural and communicative factors. We hypothesize that the socio-cultural factors induce change, whereas the communicative factors define the direction of change. In this research, we develop generative models of l...
- Constructing Intelligent Agents in Simulated Worlds
- The project aims at constructing intelligent agents in sophisticated
simulated worlds through biologically inspired computation
methods. Despite successes in structured domains like board games and
medical diagnosis, traditional artificial intelligence (AI) techniques
are unlikely to lead to ...
- Forming Text Representations with Neural Networks
- This research is concerned with the use of a neural network model to form meaningful representations of the content of documents available electronically. The goal is to show that these representations are well-suited for text management tasks such as categorization, evaluation, retrieval, and qu...
- Organization and Disorders of the Mental Lexicon: The DISLEX System
- DISLEX was originally developed as the lexicon component for the DISCERN system. It was later extended into a more complete model of the mental lexicon, including semantic, orthographic, and phonological lexical modalities. The organization of each modality and the mappings between them are learn...
- Semantic Disambiguation in Sentence Processing
- Subsymbolic processing of sentences is based on associations of words with past context. As words come in, their possible contexts are combined into the interpretation of the sentence. This model demonstrates how context frequency drives the process of disambiguating word meanings.
- Understanding Sentences with Relative Clauses: The SPEC System
- SPEC is based on the idea that sentence understanding is a controlled process. In SPEC, subsymbolic networks for parsing, memory, and control are integrated into a large modular system that learns to understand sentences with complex relative clause structure. SPEC shows how productive and system...
- Processing Script-Based Stories: The DISCERN System
- Much of our NLP work originates from DISCERN, a large-scale natural language processing system implemented entirely at the subsymbolic level. In DISCERN, distributed neural network models of parsing, generating, reasoning, lexical processing, and episodic memory are integrated into a single syste...
- Learning Word Meanings: The FGREP Method
- With FGREP, distributed representations for words are developed as part of the task. The representations reflect how the words are used in the task, and in this sense, also stand for the meanings of the words: words that are used the same way have similar representations. FGREP representations le...
- Learning Schemas for Robot Perception
- Many AI researchers have claimed that perception and thought are mediated through large scale, compositional, competitive knowledge structures known variously as frames (Minsky), scripts (Schank), or schemata (Rumelhart). Traditional AI systems hand-engineer these structures ...
- CLA: The Constructivist Learning Architecture
- The Constructivist Learning Architecture (CLA) is a model of infant cognitive development. This model is based on a constructivist information-processing approach to cognitive development, which postulates that Piagetic stages of development are a characteristic of infants' l...
- Schema-Based Object Recognition and Scene Analysis: The VISOR System
- VISOR is a large connectionist system that shows how visual schemas can be learned, represented, and used through mechanisms natural to neural networks. Processing in VISOR is based on cooperation, competition, and parallel bottom-up and top-down activation of schema represe...
- Self-Organization Driven by Internally-Generated Patterns
- Work with the RF-LISSOM model has shown that it can develop realistic cortical structures when presented with approximations of the visual environment. However, the brain already has significant structure at birth, so environmental inputs cannot account for all of this self-organization. This o...
- GLISSOM: Modeling Large Cortical Maps
- Densely-connected self-organizing models of the cortex can be quite computationally intensive to simulate. We are working on two methods for making such simulations more practical. First, we have derived a set of scaling equations that allows small networks to be used as approximations for larg...
- Segmentation and Binding: the SLISSOM Model
- SLISSOM is an extension of the LISSOM (or RF-LISSOM) model where the standard firing-rate neurons have been replaced by spiking neurons with leaky integrator synapses. The SLISSOM network self-organizes like the others but it can also represent segmentation and binding through synchronization and...
- Tilt Aftereffects in the RF-LISSOM Model
- If self-organizing processes continue operating on the adult RF-LISSOM structure, tilt aftereffects can be modeled as a result of adapting lateral inhibition and re-normalization. Simulations show that the model can account for both the direct (small angle) and indirect (large angle) effects, wh...
- Orientation Perception in the RF-LISSOM Model
- In conjunction with research on the tilt aftereffect, a number of visualizations of orientation perception have been developed. These demonstrate how perception may be occurring in the adult cortex, with a level of detail not possible to achieve with current biological and psychophysical measur...
- Self-Organization in the Primary Visual Cortex: The RF-LISSOM Model
- In RF-LISSOM, the neurons receive inputs from local receptive fields on the retina instead of the entire retina as in SOM and LISSOM. This extension leads to realistic modeling of how the receptive fields develop into orientation, ocularity, and size detectors, how the neurons become globally or...
- Semantic Effect on Episodic Associations
- Based on empirical results, we are developing a model of how humans form episodic associations between words, and how such associations are affected by existing semantic memory. A spreading activation process on a self-organizing map of word meanings matches the experiments well, and leads to sev...
- Structure and Capacity of Hippocampal Memory: The Convergence-Zone model
- Inspired by Damasio's convergence-zone idea, the inputs to the memory are assumed to be represented locally in perceptual maps, and the memory encoding is a sparse random pattern in the hippocampus. Such a memory can be analyzed mathematically and simulated computationally, and it suggests how th...
- Storing Information on Maps: The Trace Feature Map Model
- The Trace Feature Map is a self-organizing map where lateral connections between units are used to encode a memory trace: the map remembers that at some point, an input was received that was mapped at a particular location on the map. The Trace Map model was originally developed as the episodic m...
- Solving Non-Markov Control Tasks
- Most sequential decisions tasks in the real world, such as manufacturing and robot control short-term memory. Such controllers are difficult to design by traditional engineering or even conventional reinforcement learning methods because the environments are often non-linear, high-dimensio...
- Utilizing Population Culture in Neuroevolution
- Any transmission of behavior from one generation to the next via a non-genetic means is a process of culture. Culture provides major advantages for survival in the biological world. In this project, four methods were developed to harness the mechanisms of culture in neuroevolution: culling overla...
- Refinement and On-Line Adaptation of Neurocontrollers Through Particle swarming
- Although neuroevolution is powerful in discovering competent neurocontrollers, it is difficult to achieve (1) high accuracy, and (2) on-line adaptation to changes in the environment. In this project, local adaptation using Particle Swarming is shown to solve both problems. A competent neurocontr...
- Evolving Confident Neural Networks
- In standard neuroevolution, the goal is to evolve a single neural network that is often able to compute a desired answer. The method of confidence attempts to extract even better answers from the entire population. One way to do this is do evolve networks that output not only their answer, but ...
- Eugenic Evolution: The EuA, EuSANE, and TEAM
- In standard evolutionary algorithms, new individuals are generated by random mutation and recombination. In Eugenic Evolution, individuals are systematically constructed to maximize fitness, based on historical data on correlations between allele and fitness values. This method, Eugenic Algorith...
- Symbiotic Evolution: The SANE System
- In this project we developed an Evolutionary Reinforcement Learning method called SANE (Symbiotic, Adaptive Neuro-Evolution) where a population of neurons is evolved to form a neural network for a sequential decision task. Symbiotic evolution promotes both cooperation and specialization in the po...
- Marker-Based Encoding of Neural Networks
- In a marker-based encoding of a neural network, each neuron definition consists of a collection of connections specified between a start and an end marker in the chromosome. This mechanism allows all aspects of the network structure, including the number of nodes and their connectivity, to be evo...
- Nonlinear, Adaptive Process Control
- Automatic process control in the metallurgical and chemical industries is difficult for two reasons: (1) the processes are nonlinear, and (2) they change over time. In this project, neuroevolution techniques were developed to deal with both problems, using a bioreactor process as a domain. Symbio...
- Creating Melodies with Evolving Recurrent Networks
- Music composition is a domain well-suited for evolutionary reinforcement learning. It is possible to write down rules for good melodies, and those rules can be used as a fitness function. Our initial results shows that the networks learn to express primitive rules on tonality and rhythm this way...
- Playing Go
- Using the SANE and ESP methods, we have evolved networks to play go on small boards. When evolved against a computer program, the networks quickly learn to utilize weaknesses in the opponent, and exhibit aspects of general go-playing behavior. With fitness sharing, shared sampling, and hall-of-fa...
- Natural Deduction
- Natural deduction is essentially a sequential decision task, similar to many game-playing tasks. In this project, SANE was used to evolve neural networks to identify steps in a natural deduction proof. Incremental evolution through progressively more challenging problems resulted in more effecti...
- Controlling Chaos
- A version of SANE was used to evolve feedback controllers for chaotic systems. Standard methods for this task require an analytical description of the system near the fixed point. In contrast, the SANE networks were able to stabilize unstable fixed points for logistic and Henon maps under noise, ...
- Robot Control
- SANE has been used to evolve robot controllers in two simulated environment: reaching for a target while avoiding obstacles with the Simderella robot arm, and for running in a maze environment with the Khepera miniature mobile robot simulator. In both cases, evolution discovered a general, robust...
- Playing Othello
- When evolved against a positional strategy of Iago, evolution discovered how to turn the initial disadvantage in material into a novel advantage: mobility strategy. Neuroevolution can also be used to improve play of existing programs in novel ways: for example, a network can be evolved to filter ...
- LISSOM: Laterally Interconnected Self-Organizing Maps
- LISSOM is a biologically more realistic implementation of the SOM idea, where the weight change neighborhood is determined through competition and collaboration mediated by lateral connections (instead of a global supervisor), and weights are changed based on Hebbian learning and renormalization ...
- IGG: Visualization with Incremental Grid Growing
- In IGG, the 2-D lattice of the SOM is gradually grown one node at a time as part of the self-organizing process. The resulting network structure will also represent both the clusters in the data and their topology, and unlike with other growing SOM methods, it is planar (i.e. drawable). These pr...
- Vision-Driven Development of Auditory Spatial Maps
- In the barn owl, the self-organization of the auditory map is strongly influenced by vision. In this study we showed how visual attention could filter the learning in the auditory map, resulting in maps similar to those found in experimental studies. The result provides computational evidence for...
- SARDNET: Forming Maps of Sequences
- In SARDNET, a sequence of inputs is mapped to different locations on the map and gradually decayed, resulting in a compact representation of the sequence. Similar sequences are mapped to similar patterns, making it possible to perform robust speech recognition, and implement a sequence memory for...
- HFM: Hierarchical Features Maps
- If the data is strongly hierarchical, visualizing it on a flat SOM may make the hierarchy hard to see. With HFM, a hierarchy of maps is self-organized, with the high-level categories separated on top, and gradually more fine distinctions in the bottom. For example script-based story data can be v...
- Adaptive Packet Routing: The Confidence-Based Dual Reinforcement Q-Learning Algorithm
- Standard reinforcement learning (TD or Q learning) is based on forward exploration: later estimates are used to update earlier ones. In Dual Reinforcement Learning, backward exploration is also utilized: earlier estimates are used to update later estimates. The quality of estimates can be further...
- Realtime Continuous Adaptive Behavior: The Rodney System
- This project is an exploration of non-symbolic learning as applied to a robot in an environment. By modifying a Braitenburg architecture with Hebbian learning techniques whcih take advantage of the stimuli and constraints of the world, a system is devised that is exceedingly...
- On-Line Adaptation of a Signal Predistorter through Dual Reinforcement Learning
- A novel reinfrocement learning method was developed where two communicating systems could learn to predistort their signals to compensate for distortion in the channel. The two predistorters co-adapt using the output of the other predistorter to determine their own reinforcement signal. This appr...
- Intrusion Detection
- A neural net was trained with backpropagation to identify users in a multi-user unix system, based on the shell commands they used during a login session. The trained network recognized unusual activity reliably, suggesting that user profiles is a good way to detect novel attacks.
- Data Rectification for Process Control
- An SRN network was trained to predict the measurements of a dynamical system. After training, the output of the SRN could be used to rectify noise in the measurements. Importantly, such rectification is possible without explicit knowledge of the system dynamics.
- Neural Network Models of Schizophrenic Language
- Very little is known about the underlying causes of schizophrenia. Currently, the most reliable means for diagnosing schizophrenia is to observe certain disturbances of language, such as (1) positive thought disorder (i.e. derailed conversational language), (2) delusion formation of the idee fix...
- Computational Maps in the Visual Cortex
- Computational Maps in the Visual Cortex is a recent book by Miikkulainen, Bednar, Choe, and Sirosh, published by Springer in 2005. Here is the website for the book, which includes the table of contents, sample chapter, figures, references, de...
- NERO: NeuroEvolving Robotic Operatives
- The goal of the NERO project is to demonstrate how Artificial Intelligence can be used effectively in games. NERO is a game prototype where an AI technique called Neuroevolution is used to train simulated robotic agents to cope with changing environments and situations. The agents operate auton...
- SODA: Self-Organizing Distinctive State Abstraction
- A major current challenge in reinforcement learning research is to extend methods that work well on discrete, short-range, low-dimensional problems to continuous, highdiameter, high-dimensional problems, such as robot navigation using high-resolution sensors. Using SODA an robot in a continuous w...
- Learning Navigation for Personal Satellite Assistant using Neuroevolution
- The Personal Satellite Assistant (PSA) is a small robot that is designed to aid the astronauts in daily life and in carrying out experiments and maintenance in the space shuttle or space station.
Navigation is made difficult by the arrangement of thrusters on the PSA. Only forward and leftward t...
- Modular Neuroevolution for Multilegged Locomotion
- Legged robots are useful in tasks such as search and rescue because
they can effectively navigate on rugged terrain. However, it is
difficult to design controllers for them that would be stable and
robust. Learning the control behavior is difficult because optimal
behavior is not ...
- Leveraging Human Creativity with Machine Discovery
- A challenge in machine learning is to devise methods that allow
incorporating human insight into the automated learning process.
Current learning methods employ representations that make it
difficult to encode simplification and specific examples, and
learning is based on random explorati...
- Computational and Behavioral Evidence for Bilingual Aphasia Rehabilitation
- One goal of the Healthy People 2010 program is to reduce health
disparities across different segments of the population. Diagnosis and
treatment of bilingual aphasia is one area where disparities continue
to exist even though this topic is of great importance in an
increasingly bilingual worl...
- Controlling a Finless Rocket Through Neuroevolution
- Neuroevolution is a powerful method for constructing controllers for nonlinear domains. In this project, the ESP neuroevolution approach is applied to a particular challenging such domain in the real world, controlling a rocket that has no fins. Without fins, the rocket has less drag and flies hi...
- Evolving Locomotion Controllers for Multilegged Robots
- Designing stable and robust controllers for multilegged robots is a
challenging task, and it would be desirable to develop automated
methods for doing it. Learning the control behavior is difficult
however because optimal behavior is not known, and the search space
is too large for rei...
Texas Action Group
- Reasoning about Actions and Change: The Causal Calculator
- The Causal Calculator (CCalc) is a system for representing commonsense knowledge about action and change. It implements a fragment of the causal logic.
- Modular Reasoning about Actions: MAD --- the Modular Action Description language
- The Modular Action Description language MAD is a descendant of the C action language and of the Causal Calculator (CCalc). MAD extends C by adding the capability to split action descriptions into modules, and allowing action/fluent constants to be redefined during the process of "importing" a ...
- SAT-based Answer Set Programming: System Cmodels
- Answer set solver Cmodels is a system that computes answer sets for
disjunctive logic programs. Cmodels uses a SAT solver as a search engine for
enumerating models of the logic program -- possible solutions, in case of
disjunctive programs SAT solver zChaff is also used for verifying the
minimali...
