Aspects of the disclosure are directed to a system for classifying software as malicious or benign based on predicting the effect the software has on the platform before the software is actually deployed. A system as described herein can operate in close to real-time to receive, isolate, and classify software as benign or malicious. Aspects of the disclosure provide for accurate classification of malicious programs or scripts even if ostensibly the program appears benign, and vice versa, based on the effect predicted by a machine learning model trained as described herein. The system can also be implemented to isolate and verify incoming scripts or software to the platform, to provide a predicted classification while not substantially impacting processing pipelines involving platform resources or the user experience with the platform in general.

Aspects of the disclosure are directed to a system for classifying software as malicious or benign based on predicting the effect the software has on the platform before the software is actually deployed. A system as described herein can operate in close to real-time to receive, isolate, and classify software as benign or malicious. Aspects of the disclosure provide for accurate classification of malicious programs or scripts even if ostensibly the program appears benign, and vice versa, based on the effect predicted by a machine learning model trained as described herein. The system can also be implemented to isolate and verify incoming scripts or software to the platform, to provide a predicted classification while not substantially impacting processing pipelines involving platform resources or the user experience with the platform in general.

Methods and apparatus for performing machine learning tasks, and in particular, to a neural-network-processing architecture and circuits for improved handling of partial accumulation results in weight-stationary operations, such as operations occurring in compute-in-memory (CIM) processing elements (PEs). One example PE circuit for machine learning generally includes an accumulator circuit, a flip-flop array having an input coupled to an output of the accumulator circuit, a write register, and a first multiplexer having a first input coupled to an output of the write register, having a second input coupled to an output of the flip-flop array, and having an output coupled to a first input of the first accumulator circuit.

Methods and apparatus for performing machine learning tasks, and in particular, to a neural-network-processing architecture and circuits for improved handling of partial accumulation results in weight-stationary operations, such as operations occurring in compute-in-memory (CIM) processing elements (PEs). One example PE circuit for machine learning generally includes an accumulator circuit, a flip-flop array having an input coupled to an output of the accumulator circuit, a write register, and a first multiplexer having a first input coupled to an output of the write register, having a second input coupled to an output of the flip-flop array, and having an output coupled to a first input of the first accumulator circuit.

Systems and methods for an On-Demand Autonomy (ODA) service. The system includes a set of functional modules enabled for ODA service activities disposed in a follower vehicle (Fv) in communication with an ODA server that includes a user request module configured to receive request information from the Fv from the ODA server, and to process and communicate the request information to the schedule module; the schedule module configured to coordinate an arrival time information with the ODA server for pickup of the Fv based on the request information, and communicate the arrival time information to the schedule execution module; the schedule execution module configured to direct the Fv to a pickup point based on the arrival time information, and communicate the pickup point to the indication module; and the indication module configured to provide alerts to vehicles in the vicinity of the pickup of the Fv via the ODA service.

One or more outputs from a planning module of an ADV are received. Data of a driving environment of the ADV is received. A performance of the planning module is evaluated by determining a score of the performance of the planning module based on the data of the driving environment and the one or more outputs from the planning module. Whether the one or more outputs from the planning module violates at least one of a set of safety rules is determined. The score is determined being larger than a predetermined threshold in response to determining that the one or more outputs from the planning module violate at least one of the set of safety rules. Otherwise, the score is determined based on a machine learning model. The planning module is modified by tuning a set of parameters of the planning module based on the score.

An online concierge system trains a machine learning conversion model that predicts a probability of receiving an order from a user when the user accesses the online concierge system. The conversion model predicts the probability of receiving the order based on a set of input features that include price and availability information. For each access to the online concierge system, the online concierge system applies the conversion model to a current price and availability and to an optimal price availability. The online concierge system generates a metric as the difference between the two predicted probabilities of receiving an order.

Apparatuses, systems, and techniques to detect loops in neural network graphs. In at least one embodiment, one or more loops are detected within one or more graphs corresponding to one or more neural networks.

Apparatuses, systems, and techniques to detect loops in neural network graphs. In at least one embodiment, one or more loops are detected within one or more graphs corresponding to one or more neural networks.

A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.