Abstract: How does a brain work? How does the brain learn? How does its consciousness arise? Is the consciousness required by learning? Holistic computational models for the four questions are still largely missing. Neural networks models are numerous, but they do not holistically address the four questions. Holistically and approximately addressing above four questions, the brain-developmental model here consists of a Developmental Network 3 (DN-3) that grows from a single cell and goes through prenatal and postnatal developments with a fully fluid architecture for any consciousness. The network becomes increasingly conscious through on-the-fly activities including brain-patterning—automatic inside a closed skull. The model provides a surprising insight into how consciousness is recursively necessary by brain's learning at each instant, called “Conscious Learning”.

Abstract: Traditionally, learning speech synthesis and speech recognition were investigated as two separate tasks. This separation hinders incremental development for concurrent synthesis and recognition, where partially-learned synthesis and partially-learned recognition must help each other throughout lifelong learning. This invention is a paradigm shift—we treat synthesis and recognition as two intertwined aspects of a lifelong learning robot. Furthermore, in contrast to existing recognition or synthesis systems, babies do not need their mothers to directly supervise their vocal tracts at every moment during the learning. We argue that self-generated non-symbolic states/actions at fine-grained time level help such a learner as necessary temporal contexts. Here, we approach a new and challenging problem—how to enable an autonomous learning system to develop an artificial motor for generating temporally-dense (e.g., frame-wise) actions on the fly without human handcrafting a set of symbolic states.

Abstract: This invention presents a new kind of robots that learn in real-time, on the fly, without a need for either annotation of sensed images or annotation of motor images. Therefore, during the process of learning, such annotation-free robots are always conscious throughout its lifetime. This invention grew from the prior art called Developmental Networks that has already supported by its Emergent Turing Machine under-pinning and the maximum-likelihood property. These key properties make it practical to close the loop—from 3D world to 2D sensory images and motor images and back to 3D world. This invention seems to be the first algorithmic-level, holistic, and neural network model for developing machine consciousness. Furthermore, this model is through conscious learning and freedom from annotations of sensory images and motor images. This invention appears to be also the first to model animal-like discovery through general-purpose imitation.

Abstract: This invention presents a method and an apparatus for auto-programming for general purposes as well as a new kind of operating system that uses a general-purpose learning engine to learn any open-ended practical tasks or applications. Experimental systems of the method are applied to vision, audition, and natural language understanding.

Abstract: The term instantaneous in this invention means that the roughly 180° horizontal visual field of view that a human senses in real time. The major novelty of the instantaneous 180° (i180°) 3D technology includes (a) a combination of multiple binocular and monocular fields of view for image acquisition, (b) a combination of binocular and monocular fields of view in content playback, (c) a multi-resolution scheme for sensing, processing, transmission, and playback, (d) a realization of physical consistency of the line of sight with minimal distortion of all projection lines between imaging and display, and (e) a method for two-way compatibility for systems with conventional binocular 3D and monocular 2D systems. In addition to applications in consumer electronics, the invention has potential applications in professional business, such as film industry, theaters, museums, advertisements, surgery, rehabilitation, and assistance to the handicapped and elderly.

Abstract: This invention includes a new type of neural network that is able to automatically and incrementally generate an internal hierarchy without a need to handcraft a static hierarchy of network areas and a static number of levels and the static number of neurons in each network area or level. This capability is achieved by enabling each neuron to have its own dynamic inhibitory zone using neuron-specific inhibitory connections.

Abstract: The Developmental Network incorporates a Turing Machine that injects teaching instructions directly into the skull-closed network. The Developmental Network can also autonomously learn directly from the natural world without the need for a human to encode its input and output. The neural network so configured can be used as a controller for robotic and other computer control applications where the neural network is organized into plural X-Y-Z areas receiving signals from sensors and providing signals to effectors.

Abstract: The term instantaneous in this invention means that the roughly 180° horizontal visual field of view that a human senses in real time. The major novelty of the instantaneous 180° (i180°) 3D technology includes (a) a combination of multiple binocular and monocular fields of view for image acquisition, (b) a combination of binocular and monocular fields of view in content playback, (c) a multi-resolution scheme for sensing, processing, transmission, and playback, (d) a realization of physical consistency of the line of sight with minimal distortion of all projection lines between imaging and display, and (e) a method for two-way compatibility for systems with conventional binocular 3D and monocular 2D systems. In addition to applications in consumer electronics, the invention has potential applications in professional business, such as film industry, theaters, museums, advertisements, surgery, rehabilitation, and assistance to the handicapped and elderly.

Abstract: The Developmental Network incorporates a Turing Machine that injects teaching instructions directly into the skull-closed network. The Developmental Network can also autonomously learn directly from the natural world without the need for a human to encode its input and output. The neural network so configured can be used as a controller for robotic and other computer control applications where the neural network is organized into plural X-Y-Z areas receiving signals from sensors and providing signals to effectors.

Abstract: The developmental neural network is trained using a synaptic maintenance process. Synaptogenic trimming is first performed on the neuron inputs using a synaptogenic factor for each neuron based on standard deviation of a measured match between the input and synaptic weight value. A top-k competition among all neurons then selects a subset of said neurons as winning neurons. Neuronal learning is applied only to these winning neurons, updating their synaptic weights and updating their synaptogenic factors.

Abstract: In various embodiments, electronic apparatus, systems, and methods include a unified compact spatiotemporal method that provides a process for machines to deal with space and time and to deal with sensors and effectors. Additional apparatus, systems, and methods are disclosed.

Abstract: In various embodiments, electronic apparatus, systems, and methods include a unified compact spatiotemporal method that provides a process for machines to deal with space and time and to deal with sensors and effectors. Additional apparatus, systems, and methods are disclosed.

Abstract: The developmental neural network is trained using a synaptic maintenance process. Synaptogenic trimming is first performed on the neuron inputs using a synaptogenic factor for each neuron based on standard deviation of a measured match between the input and synaptic weight value. A top-k competition among all neurons then selects a subset of said neurons as winning neurons. Neuronal learning is applied only to these winning neurons, updating their synaptic weights and updating their synaptogenic factors.

Abstract: An in-place learning algorithm is provided for a multi-layer developmental network. The algorithm includes: defining a sample space as a plurality of cells fully connected to a common input; dividing the sample space into mutually non-overlapping regions, where each region is a represented by a neuron having a single feature vector; and estimating a feature vector of a given neuron by an amnesic average of an input vector weighted by a response of the given neuron, where amnesic is a recursive computation of the input vector weighted by the response such that the direction of the feature vector and the variance of signal in the region projected onto the feature vector are both recursively estimated with plasticity scheduling.

Abstract: An in-place learning algorithm is provided for a multi-layer developmental network. The algorithm includes: defining a sample space as a plurality of cells fully connected to a common input; dividing the sample space into mutually non-overlapping regions, where each region is a represented by a neuron having a single feature vector; and estimating a feature vector of a given neuron by an amnesic average of an input vector weighted by a response of the given neuron, where amnesic is a recursive computation of the input vector weighted by the response such that the direction of the feature vector and the variance of signal in the region projected onto the feature vector are both recursively estimated with plasticity scheduling.

Abstract: A machine and method capable of developing intelligent behavior from interaction with its environment directly using the machine's sensors and effectors. The method described is independent of the type of sensors and actuators, or the tasks to be executed, and, therefore, provides a general purpose learner that learns while performing. It senses the world, recalls what is learned, judges what to do and acts according to what it has learned. The machine enables the machine to learn directly from sensory input streams while interacting with the environment, including human teachers. The presented approach enables the system to self-organize its internal representation, and uses a systematic way to automatically build multi-level representation using the Markov random process model. Reward and punishment are combined with sensor-based teaching to develop intelligent behavior.

Abstract: A method and system for building virtual reality object models. The method includes defining an object space, generating multiple two-dimensional real images of the object, and selecting multiple reference points in each image, the reference points defining an image region, the region having a texture. The method also includes determining the three-dimensional position in the object space of each of the reference points in each image, the positions determined defining a model surface, mapping the texture of an image region onto a model surface, and generating a three-dimensional model of the object using the determined positions and the mapped texture. The system includes one or more cameras, a calibration apparatus, a graphic interface and software for performing the method.