Abstract: Methods for operating a neural network on processors are provided. Methods may include creating a neural network. The neural network may include a plurality of neurons. Each neuron may represent a data point. Each neuron may be sorted in a hierarchical tree. The sorting may be based on attributes of the data points. The tree may include a plurality of decision forks. Each fork may represent a differentiator between a data point type that categorizes the data points. Methods may receive an additional data point to append to the tree. Methods may receive metadata relating to a categorization of the additional data point. Methods may convert the additional data point to a neuron. Methods may add the neuron to the tree at a bottom edge of the tree. Methods may flatten the tree into a flattened neuron network. Methods may replace the neural network with the flattened neural network.

Abstract: Apparatus and methods for a pattern identification transformer neural network is provided. The pattern identification transformer neural network may be able to learn from relatively small numbers of data elements. The pattern identification transformer neural network may function in similar method to the way humans transform data points. As such, the pattern identification transformer neural network may be able to learn patterns from a small number of examples and determine what attributes are helpful from a single experience. The pattern identification transformer neural networks may include a multi-head attention module, a normalize module and a feed forward neural network. The multi-head attention module may receive vectors that correspond to experiences. The normalize module may normalize the received vectors. The feed forward neural network may incorporate the received vectors into the neural network.

Abstract: Apparatus and methods for a pattern identification transformer neural network is provided. The pattern identification transformer neural network may be able to learn from relatively small numbers of data elements. The pattern identification transformer neural network may function in similar method to the way humans transform data points. As such, the pattern identification transformer neural network may be able to learn patterns from a small number of examples and determine what attributes are helpful from a single experience. The pattern identification transformer neural networks may include a multi-head attention module, a normalize module and a feed forward neural network. The multi-head attention module may receive vectors that correspond to experiences. The normalize module may normalize the received vectors. The feed forward neural network may incorporate the received vectors into the neural network.

Abstract: A method for generating a simplex from a plurality of neurons is provided. Methods may receive the neurons. Each neuron may encode a data point. Methods may receive a new data point and project the new data point on the neurons. A reconstruction error value may be generated from the projection of the new data point onto the neurons. The reconstruction error value may quantify the new data point. Methods may include creating a coactivation matrix for the neurons and the reconstruction error value. Methods may invert the coactivation matrix, and identify, from the inverted coactivation matrix, coordinates for each end point of a simplex. Methods may generate a simplex from the coordinates. Methods may receive a data structure and plot the data structure within the simplex. Methods may identify a correspondence value between the data structure and the end points, the correspondence values may add up to 100%.

Abstract: A resource conservation system, including a determination processor may be provided. The determination processor may identify a characterization output that characterizes a plurality of data structures. The characterization output may be based on plurality of inputs. The inputs may be processed through a plurality, or cascade, of artificial intelligence models both in sequence and in parallel. A numerical value may be identified for each data structure. The value may identify a degree of certainty that the determination processor accurately characterized each data structure. When the degree is above a threshold, the determination processor may identify a subset of inputs that most contributed to the characterization output. The determination processor may execute an equation to identify a subset of inputs that most contributed to the output. The equation may involve inputs and/or outputs of each of the cascade of models. Identified inputs may be ranked based on contribution to the outcome.

Abstract: A method for candidate data points selection for labeling unlabeled data points is provided. The method may include inputting a first data point to an auditable neural network. The method may include predicting, using the network, a label for the first data point. The method may include deconstructing, based on a simplicial structure, the first data point into a plurality of component parts of the first data point. The method may include reconstructing, the first data point into a reconstructed first data point, based on the simplicial structure, using the plurality of component parts and the label. The method may include generating a reconstruction error value based on a reconstruction error algorithm that compares the first data point to the reconstructed first data point. The method may include quarantining the first data point within the auditable neural network when the reconstruction error value is above a threshold reconstruction error value.

Abstract: A resource conservation system, including a determination processor may be provided. The determination processor may identify a characterization output that characterizes a plurality of data structures. The characterization output may be based on plurality of inputs. The inputs may be processed through a plurality, or cascade, of artificial intelligence models both in sequence and in parallel. A numerical value may be identified for each data structure. The value may identify a degree of certainty that the determination processor accurately characterized each data structure. When the degree is above a threshold, the determination processor may identify a subset of inputs that most contributed to the characterization output. The determination processor may execute an equation to identify a subset of inputs that most contributed to the output. The equation may involve inputs and/or outputs of each of the cascade of models. Identified inputs may be ranked based on contribution to the outcome.

Abstract: A resource conservation system, including a determination processor may be provided. The determination processor may identify a characterization output that characterizes a plurality of data structures. The characterization output may be based on plurality of inputs. The inputs may be processed through a plurality, or cascade, of artificial intelligence models both in sequence and in parallel. A numerical value may be identified for each data structure. The value may identify a degree of certainty that the determination processor accurately characterized each data structure. When the degree is above a threshold, the determination processor may identify a subset of inputs that most contributed to the characterization output. The determination processor may execute an equation to identify a subset of inputs that most contributed to the output. The equation may involve inputs and/or outputs of each of the cascade of models. Identified inputs may be ranked based on contribution to the outcome.

Abstract: Apparatus and methods for a pattern identification transformer neural network is provided. The pattern identification transformer neural network may be able to learn from relatively small numbers of data elements. The pattern identification transformer neural network may function in similar method to the way humans transform data points. As such, the pattern identification transformer neural network may be able to learn patterns from a small number of examples and determine what attributes are helpful from a single experience. The pattern identification transformer neural networks may include a multi-head attention module, a normalize module and a feed forward neural network. The multi-head attention module may receive vectors that correspond to experiences. The normalize module may normalize the received vectors. The feed forward neural network may incorporate the received vectors into the neural network.

Abstract: Apparatus and methods for harnessing an explainable artificial intelligence system to execute computer-aided feature selection is provided. Methods may receive an AI-based model. The AI-based model may be trained with a plurality of training data elements. The AI-based model may identify a set of features from the training data elements. The AI-based model may execute with respect to a first input. Methods may use a cascade model with integrated gradients to identify a feature importance value for each of the plurality of features included in the training data. Based on the feature importance value identified for each feature, methods may determine a feature importance metric level. Based on the feature importance value identified for each feature, methods may remove features that are assigned a value lower than the feature importance metric level. This removal may be implemented to form a revised AI-based model. Methods may execute the revised AI-based model.

Abstract: A resource conservation system, including a determination processor may be provided. The determination processor may identify a characterization output that characterizes a plurality of data structures. The characterization output may be based on plurality of inputs. The inputs may be processed through a plurality, or cascade, of artificial intelligence models both in sequence and in parallel. A numerical value may be identified for each data structure. The value may identify a degree of certainty that the determination processor accurately characterized each data structure. When the degree is above a threshold, the determination processor may identify a subset of inputs that most contributed to the characterization output. The determination processor may execute an equation to identify a subset of inputs that most contributed to the output. The equation may involve inputs and/or outputs of each of the cascade of models. Identified inputs may be ranked based on contribution to the outcome.

Abstract: A canoe caddy having a frame adapted to support one end of a canoe or boat thereon, front ground-engaging wheels, and rear ground-engaging wheels. The frame is held straight over the top of the wheels in a first position which is useful for attaching one end of a canoe in an inverted position thereon, for moving such canoe near a vehicle, and for loading such canoe onto or off from a car top carrier or the like. Once the canoe and caddy are loaded onto such car top carrier, then the caddy can be folded to a more compact position. The caddy is also useful in a third position whereby the frame is rotated over the front wheels thereof for receiving a canoe in an upright position on one end thereof for permitting one person to easily transport the canoe to the water's edge for launching such canoe into the water using such caddy.

Abstract: A canoe caddy having a frame adapted to support one end of a canoe or boat thereon, front ground-engaging wheels, and rear ground-engaging wheels. The frame is held straight over the top of the wheels in a first position which is useful for attaching one end of a canoe in an inverted position thereon, for moving such canoe near a vehicle, and for loading such canoe onto or off from a car top carrier or the like. Once the canoe and caddy are loaded onto such car top carrier, then the caddy can be loaded to a more compact position. The caddy is also useful in a third position whereby the frame is rotated over the front wheels thereof for receiving a canoe in an upright position on one end thereof for permitting one person to easily transport the canoe to the water's edge for launching such canoe into the water using such caddy.