Yilu Zhang

Candid covariance-free incremental principal component analysis

Appearance-based image analysis techniques require fast computation of principal components of high-dimensional image vectors. We introduce a fast incremental principal component analysis (IPCA) algorithm, called candid covariance-free IPCA (CCIPCA), used to compute the principal components of a sequence of samples incrementally without estimating the covariance matrix (so covariance-free). The new method is motivated by the concept of statistical efficiency (the estimate has the smallest variance given the observed data). To do this, it keeps the scale of observations and computes the mean of observations incrementally, which is an efficient estimate for some well known distributions (e.g., Gaussian), although the highest possible efficiency is not guaranteed in our case because of unknown sample distribution. The method is for real-time applications and, thus, it does not allow iterations. It converges very fast for high-dimensional image vectors. Some links between IPCA and the development of the cerebral cortex are also discussed.

Task Transfer by a Developmental Robot

Scaffolding is a process of transferring learned skills to new and more complex tasks through arranged experience in open-ended development. In this paper, we propose a developmental learning architecture that enables a robot to transfer skills acquired in early learning settings to later more complex task settings. We show that a basic mechanism that enables this transfer is sequential priming combined with attention, which is also the driving mechanism for classical conditioning, secondary conditioning, and instrumental conditioning in animal learning. A major challenge of this work is that training and testing must be conducted in the same program operational mode through online, real-time interactions between the agent and the trainers. In contrast with former modeling studies, the proposed architecture does not require the programmer to know the tasks to be learned and the environment is uncontrolled. All possible perceptions and actions, including the actual number of classes, are not available until the programming is finished and the robot starts to learn in the real world. Thus, a predesigned task-specific symbolic representation is not suited for such an open-ended developmental process. Experimental results on a robot are reported in which the trainer shaped the behaviors of the agent interactively, continuously, and incrementally through verbal commands and other sensory signals so that the robot learns new and more complex sensorimotor tasks by transferring sensorimotor skills learned in earlier periods of open-ended development

Action chaining by a developmental robot with a value system

A developmental cognitive learning architecture with a value system is proposed for an artificial agent to learn composite behaviors upon the acquisition of basic ones. This work is motivated by researches on classical conditioning in animal learning areas. Compared to former works, the proposed architecture enables an agent to conduct learning in unknown environments through online realtime experiences. All possible perceptions and actions, including even the actual number of classes, are not available until the programming is finished and the robot starts to learn in the real world. Experiments with our SAIL (Self-organizing Autonomous Incremental Learner) robot are reported to show how a trainer instructed (or shaped) the behaviors of the agent through verbal commands.

Auditory learning: a developmental method

Motivated by the human autonomous development process from infancy to adulthood, we have built a robot that develops its cognitive and behavioral skills through real-time interactions with the environment. We call such a robot a developmental robot. In this paper, we present the theory and the architecture to implement a developmental robot and discuss the related techniques that address an array of challenging technical issues. As an application, experimental results on a real robot, self-organizing, autonomous, incremental learner (SAIL), are presented with emphasis on its audition perception and audition-related action generation. In particular, the SAIL robot conducts the auditory learning from unsegmented and unlabeled speech streams without any prior knowledge about the auditory signals, such as the designated language or the phoneme models. Neither available before learning starts are the actions that the robot is expected to perform. SAIL learns the auditory commands and the desired actions from physical contacts with the environment including the trainers.

A fast algorithm for incremental principal component analysis

We introduce a fast incremental principal component analysis (IPCA) algorithm, called candid covariance-free IPCA (CCIPCA), to compute the principal components of a sequence of samples incrementally without estimating the covariance matrix (thus covariance-free). This new method is for real-time applications where no iterations are allowed and high-dimensional inputs are involved, such as appearance-based image analysis. CCIPCA is motivated by the concept of statistical efficiency (the estimate has the smallest variance given the observed data). The convergence rate of CCIPCA is very high compared with other IPCA algorithms on high-dimensional data, although the highest possible efficiency is not guaranteed because of the unknown sample distribution.

Chained action learning through real-time interactions

The capability of learning new skills is very important for an artificial agent to scale up. In this paper, we propose a developmental cognitive learning architecture which enables an artificial agent to develop complex behaviors (chained actions) after acquisition of simple ones. The mechanism that makes this possible is chained secondary conditioning. The major challenge of this work is that training and testing must be conducted in the same mode through online real-time interactions between the agent and trainers. Experimental results on a real-time system are reported, in which the trainer shapes the behavior of the agent interactively and continuously through verbal commands and other sensory signals.

Autonomous speech acquisition of a robot

It is difficult to program a robot that understands speech. Instead of learning speech from offline speech data, online and grounded learning by a robot can potentially address the robot speech recognition issue. Motivated by the human speech acquisition process, we propose to enable a robot to learn from interactive experience. The author presents some recent results of a robot that develops its speech-related skills through real-time interactions with its environment.

Developing auditory skills by the SAIL robot

Motivated by the autonomous developmental process of higher animals and humans from infancy to adulthood, the objective of our SAIL developmental robot project is to investigate how to enable a robot to develop its cognitive and behavioral skills through online, real-time interactions with the environment. In other words, our goal is to enable a robot to learn autonomously from real-world experiences. The work presented here focuses on the development of its auditory behaviors. Both simulation results and experiments on real robot are reported.