Abstract: The technology disclosed relates to efficient tertiary analysis of genomic data. The technology disclosed includes splitting a genomic data file into a plurality of segments, and storing segments in the plurality of segments across nodes of a distributed storage system, pushing the segments from the nodes of the distributed storage system to nodes of a distributed, in-memory computing engine, distributing directives of tertiary analysis job contexts for the genomic data file across the nodes of the distributed, in-memory computing engine, directly executing the distributed directives on the segments stored on the nodes of the distributed, in-memory computing engine to cause parallel processing of the segments, and aggregating results of the parallel processing across the nodes of the distributed, in-memory computing engine to produce an output.

Abstract: Method and system with federated learning model for health care applications are disclosed. The system for federated learning comprises multiple edge devices of end users, one or more federated learner update repository, and one or more cloud. Each edge device comprises a federated learner model, configured to send tensors to federated learner update repository. Cloud comprises a federated learner model, configured to send tensors to federated learner update repository. Federated learner update repository comprises a back-end configuration, configured to send model updates to edge devices and cloud.

Abstract: The technology disclosed relates to identity designations (“akas”) for metaverse environments. In particular, the technology disclosed relates to a system that comprises a metaverse environment configured to render a plurality of digital avatars, memory storing a plurality of identity labels (“akas”), identity labels in the plurality of identity labels configured for designation to digital avatars in the plurality of digital avatars, identity designation logic configured to designate an identity label from the plurality of identity labels to an avatar in the plurality of avatars in response to a user selection of the identity label, and rendering logic configured to render the avatar in the metaverse environment with the designated identity label.

Abstract: The technology disclosed relates to a provenance system for tracing repurposing of targeted artificial intelligence (AI) systems. A training logic is configured to train an AI system on a training dataset that satisfies a target artist configuration by requiring that at least some training samples in the training dataset are sourced from a target artist, and to generate a trained version of the AI system (trained AI system). The target artist configuration characterizes a work of the target artist. The trained AI system is configured to construct an output that satisfies that target artist configuration. A deployment logic is configured to make available the trained AI system via a blockchain network. A provenance logic is configured to provide access to the trained AI system, and to validate that new outputs generated by repurposing the trained AI system satisfy the target artist configuration.

Abstract: The technology disclosed relates to a fractional ownership system for artificial intelligence systems. A fractionalization logic is configured to specify respective fractions of ownership for respective owners of an artificial intelligence system. The fractions of ownership are specified based on a plurality of architectural resolutions of an architecture of the artificial intelligence system. A credit flow logic is configured to fractionalize and allocate credit results from licensing of the artificial intelligence system to the respective owners based on the fractions of ownership.

Abstract: The technology disclosed relates to a provenance system for tracing licensing of targeted artificial intelligence (AI) systems. A training logic is configured to train an AI system on a training dataset that satisfies a target artist configuration by requiring that at least some training samples in the training dataset are sourced from a target artist, and to generate a trained version of the AI system. The target artist configuration characterizes a work of the target artist. The trained AI system is configured to construct an output that satisfies that target artist configuration. A deployment logic is configured to make available the trained AI system via a blockchain network. A provenance logic is configured to license the trained version of the artificial intelligence system to a plurality of licensees, and to validate that licensed copies of the trained version of the artificial intelligence system satisfy the target artist configuration.

Abstract: The technology disclosed provides systems and methods related to preventing exfiltration of training data by feature reconstruction attacks on model instances trained on the training data during a training job. The system comprises a privacy interface that presents a plurality of modulators for a plurality of training parameters. The modulators are configured to respond to selection commands via the privacy interface to trigger procedural calls. The procedural calls modify corresponding training parameters in the plurality of training parameters for respective training cycles in the training job. The system comprises a trainer configured to execute the training cycles in dependence on the modified training parameters. The trainer can determine a performance accuracy of the model instances for each of the executed training cycles.

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

Abstract: The technology disclosed relates to a system and method for assigning participants to groups in a clinical trial. The system includes a federated server configured with group assignability data specifying a plurality of groups assignable to participants in a clinical trial and group distribution data specifying distribution of the participants into groups. The groups include at least one placebo group and one or more treatment groups. The system includes an intervention server configured to generate group encryption keys for encrypting the group assignability data. The system includes edge devices of each of the participants. The edge devices are in communication with the federated server.

Abstract: The technology disclosed relates to systems and methods of cross-platform programming of tiny machine learning (ML) applications. The method includes providing a first declarative instruction that, when processed, interacts with a cross-platform capability of tiny ML hardware. The method includes providing a second declarative instruction that, when processed, invokes at least one procedure block. The method includes providing a third declarative instruction that, when processed, causes output from the tiny ML hardware. The method includes compiling the ML procedure block and the tiny ML model into bytecode. The bytecode interacts, via a virtual machine (VM) layer, with the capability to produce the output responsive to the first, second and third declarative instructions.

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic biometric identifiers. The method includes generating a scannable code upon receiving a success nonce from a registration server. The registration server can access a user identifier and a hash of at least a signature using the success nonce. The signature can be generated based at least in part upon a biometric identifier of a user. The method includes recreating the hash of the signature stored by the registration server. The method includes generating the scannable code by encrypting the success nonce and the recreated hash. The biometric identifier of the user is generated by feeding a plurality of non-deterministic biometric inputs to a trained machine learning model producing a plurality of feature vectors. The method includes projecting the plurality of feature vectors onto a surface of a unit hyper-sphere and computing a characteristic identity vector representing the user.

Abstract: The technology disclosed relates to systems and methods for deploying cross-platform applications to tiny ML hardware. The system provides tools to maintain definitions of a first, a second and a third declarative instruction. The system provides tools to maintain compiled bytecode for a procedure block and a tiny ML model that runs on the tiny ML hardware. The compiled bytecode further includes a manifest of one or more capabilities, one or more procedure blocks and at least one output supported by the tiny ML model. The system provides a loader that connects to an instance of the tiny ML hardware. The loader includes logic to verify that the instance of the ML hardware supports the one or more capabilities, the one or more procedure blocks and at least one output specified in the manifest. The loader loads the bytecode and verifies integrity of the load.

Abstract: The technology disclosed relates to a system and method for assigning participants to groups in a clinical trial. The system includes a federated server configured with group assignability data specifying a plurality of groups assignable to participants in a clinical trial and group distribution data specifying distribution of the participants into groups. The groups include at least one placebo group and one or more treatment groups. The system includes an intervention server configured to generate group encryption keys for encrypting the group assignability data. The system includes edge devices of each of the participants. The edge devices are in communication with the federated server.

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

Abstract: The technology disclosed relates to systems and methods for deploying cross-platform applications to tiny ML hardware. The system provides tools to maintain definitions of a first, a second and a third declarative instruction. The system provides tools to maintain compiled bytecode for a procedure block and a tiny ML model that runs on the tiny ML hardware. The compiled bytecode further includes a manifest of one or more capabilities, one or more procedure blocks and at least one output supported by the tiny ML model. The system provides a loader that connects to an instance of the tiny ML hardware. The loader includes logic to verify that the instance of the ML hardware supports the one or more capabilities, the one or more procedure blocks and at least one output specified in the manifest. The loader loads the bytecode and verifies integrity of the load.

Abstract: The technology disclosed relates to systems and methods of cross-platform programming of tiny machine learning (ML) applications. The method includes providing a first declarative instruction that, when processed, interacts with a cross-platform capability of tiny ML hardware. The method includes providing a second declarative instruction that, when processed, invokes at least one procedure block. The method includes providing a third declarative instruction that, when processed, causes output from the tiny ML hardware. The method includes compiling the ML procedure block and the tiny ML model into bytecode. The bytecode interacts, via a virtual machine (VM) layer, with the capability to produce the output responsive to the first, second and third declarative instructions.

Abstract: The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

Abstract: The technology disclosed relates to a system and method for detecting when to diverge to a tangential conversation from a linearly structured steps of a cognitive behavioral therapy (CBT) session in a series of sessions for a mental health disorder. The system includes logic to determine when to merge the tangential conversation back to flow of linearly structured steps in the therapy session. The system can bookmark the last completed step in the flow of linearly structured steps of the CBT therapy session before starting the tangential conversation. The system can calculate a return to CBT session score after each succeeding utterance from the patient in the tangential conversation. The system resumes flow of the linearly structured steps of the CBT session upon detecting that the return to CBT session score has exceeded a threshold.

Abstract: The technology disclosed relates to a system and method for remembering content received from a patient for future use and understood by computerized natural language processing during a chatbot therapy session. The system includes a graph of entities and relationships in an artificial memory graph data structure. The entity nodes in the graph represent entities that are related to a patient root node representing the patient. The entity nodes are connected to patient root node by one or more relationship edges that have named roles. The entity nodes and/or relationship edges can be slotted for at least a distinguishing name, a patient sentiment towards the entity and an entity state.