A method may include training a machine learning model to perform a first task before training the machine learning model to perform the second task. The machine learning model includes a generator network and a discriminator network. The training includes training, based on a first training sample associated with the first task, the discriminator network to perform the first task. The generator network may be trained to generate a first synthetic training sample emulating the first training sample. The discriminator network trained to perform the first task may be reinitialized in order for the discriminator network to be trained, based on a second training sample, to perform the second task. The reinitialized discriminator network may be further retrained, based on the first synthetic training sample, to perform the first task. Related systems and articles of manufacture, including computer program products, are also provided.

Embodiments of the present disclosure include a method for token-position handling comprising: processing a first sequence of tokens to produce a second sequence of tokens, wherein the second sequence of tokens has a smaller number of tokens than the first sequence of tokens; masking at least some tokens in the second sequence to produce masked tokens; moving the masked tokens to the beginning of the second sequence to produce a third sequence; encoding tokens in the third sequence into a set of numeric vectors in a first array; and processing the first array in a transformer neural network to determine correlations among the third sequence, the processing the first array producing a second array.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating neural network architectures. One of the methods includes receiving a request to determine an architecture for a task neural network; maintaining data specifying a plurality of candidate architectures for the task neural network; repeatedly performing operations comprising: selecting one or more candidate architectures in the maintained data to be modified; generating a new candidate architecture from the selected candidate architecture by, for each hyperparameter in the set of hyperparameters, selecting the value for the hyperparameter for the new candidate architecture; and adding data specifying the new candidate architecture to the maintained data; and selecting, as the final architecture for the task neural network, one of the candidate architectures specified in the maintained data.

Described is a system and method for the classification of agents based on agent movement patterns. In operation, the system receives position data of a moving agent from a camera or sensor. Motion data of the moving agent is then extracted and used to generate a predicted future motion of the moving agent using a set of pre-calculated Echo State Networks (ESN). Each ESN represents an agent classification and generates a predicted future motion. A prediction error is generated for each ESN by comparing the predicted future motion for each ESN with actual motion data. Finally, the agent is classified based on the ESN having the smallest prediction error.

Indications of sample machine learning models which create synthetic content items are provided via programmatic interfaces. A representation of a synthetic content item produced by one of the sample models in response to input obtained from a client of a provider network is presented. In response to a request from the client, a machine learning model is trained to produce additional synthetic content items.

A computer implemented method of improving parameters of a critic approximator module includes receiving, by a mixed integer program (MIP) actor, (i) a current state and (ii) a predicted performance of an environment from the critic approximator module. The MIP actor solves a mixed integer mathematical problem based on the received current state and the predicted performance of the environment. The MIP actor selects an action a and applies the action to the environment based on the solved mixed integer mathematical problem. A long-term reward is determined and compared to the predicted performance of the environment by the critic approximator module. The parameters of the critic approximator module are iteratively updated based on an error between the determined long-term reward and the predicted performance.

Systems are methods are provided for training an automated agent. The automated agent maintains a reinforcement learning neural network and generates, according to outputs of the reinforcement learning neural network, signals for communicating resource task requests. The system includes a communication interface, a processor, memory, and software code stored in the memory. The software code, when executed, causes the system to: instantiate an automated agent for communicating resource task requests; receive a current feature data structure related to a resource of the resource task requests; maintain a plurality of historical feature data structures related to said resource for a plurality of prior time steps; compute normalized feature data using the current feature data structure and the plurality of historical feature data structures; compute supplemented state data appended with the normalized feature data; and transmit said supplemented state data to the reinforcement learning neural network to train said automated agent.

Example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to select options for decisions in connection with design features of a computing device. In a particular implementation, design options for two or more design decisions of neural network processing device may be selected based, at least in part, on combination of function values that are computed based, at least in part, on a tensor expressing sample neural network weights.

The technology disclosed relates to a variant pathogenicity classifier. The variant pathogenicity classifier comprises memory and runtime logic. The memory stores (i) a reference amino acid sequence of a protein, (ii) an alternative amino acid sequence of the protein that contains a variant amino acid caused by a variant nucleotide, and (iii) a protein contact map of the protein. The runtime logic has access to the memory, and is configured to provide (i) the reference amino acid sequence, (ii) the alternative amino acid sequence, and (iii) the protein contact map as input to a first neural network, and to cause the first neural network to generate a pathogenicity indication of the variant amino acid as output in response to processing (i) the reference amino acid sequence, (ii) the alternative amino acid sequence, and (iii) the protein contact map.

An example method includes obtaining, a virtual model of a portion of an anatomy of a patient obtained from a virtual surgical plan for an orthopedic joint repair surgical procedure to attach a prosthetic to the anatomy; identifying, based on data obtained by one or more sensors, positions of one or more physical markers positioned relative to the anatomy of the patient; and registering, based on the identified positions, the virtual model of the portion of the anatomy with a corresponding observed portion of the anatomy.