Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein design. In one aspect, a method comprises: processing an input characterizing a target protein structure of a target protein using an embedding neural network having a plurality of embedding neural network parameters to generate an embedding of the target protein structure of the target protein; determining a predicted amino acid sequence of the target protein based on the embedding of the target protein structure, comprising: conditioning a generative neural network having a plurality of generative neural network parameters on the embedding of the target protein structure; and generating, by the generative neural network conditioned on the embedding of the target protein structure, a representation of the predicted amino acid sequence of the target protein.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for unmasking a masked representation of a protein using a protein reconstruction neural network. In one aspect, a method comprises: receiving the masked representation of the protein; and processing the masked representation of the protein using the protein reconstruction neural network to generate a respective predicted embedding corresponding to one or more masked embeddings that are included in the masked representation of the protein, wherein a predicted embedding corresponding to a masked embedding in a representation of the amino acid sequence of the protein defines a prediction for an identity of an amino acid at a corresponding position in the amino acid sequence, wherein a predicted embedding corresponding to a masked embedding in a representation of the structure of the protein defines a prediction for a corresponding structural feature of the protein.

Abstract: A reinforcement learning neural network system in which internal representations and policies are grounded in visual entities derived from image pixels comprises a visual entity identifying neural network subsystem configured to process image data to determine a set of spatial maps representing respective discrete visual entities. A reinforcement learning neural network subsystem processes data from the set of spatial maps and environmental reward data to provide action data for selecting actions to perform a task.

Abstract: Systems and methods are disclosed which detect unresponsive interactions with display pages. Specifically, a client computing device may retrieve display pages from a remote computing system for local display. A local interaction monitoring component may monitor local interactions with the display pages, identify those interactions that did not produce a change in the display page as unresponsive interactions, and transmit unresponsive interaction information to the remote computing system. The remote system may aggregate the unresponsive interaction information to determine unresponsive elements of the display page and modify page templates associated with the unresponsive elements to reduce unresponsive interactions.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.

Abstract: A reinforcement learning neural network system in which internal representations and policies are grounded in visual entities derived from image pixels comprises a visual entity identifying neural network subsystem configured to process image data to determine a set of spatial maps representing respective discrete visual entities. A reinforcement learning neural network subsystem processes data from the set of spatial maps and environmental reward data to provide action data for selecting actions to perform a task.

Abstract: Systems and methods are disclosed which detect unresponsive interactions with display pages. Specifically, a client computing device may retrieve display pages from a remote computing system for local display. A local interaction monitoring component may monitor local interactions with the display page, and identify those interactions with the display pages that did not produce a change in the display page as unresponsive interactions. Unresponsive interactions are monitored to determine whether a cluster of unresponsive interactions is formed around an interactive element and the size of the active area of the interactive element is increased.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.

Abstract: An approach is provided for protecting a network from a unicast flood. If the destination MAC address of a frame is not included in a table of unknown MAC addresses, the MAC address is added to the table and the frame is forwarded to non-blocked spanning tree links to find the MAC address in the network. If the MAC address is included in the table, and if a timer for suppressing forwarding of frames is active, the frame is discarded, or if the timer is inactive, a counter for counting received frames is incremented and compared to a threshold value. If the counter is greater than the threshold value, the timer is activated and the frame is discarded. If the counter is not greater than the threshold value, the frame is forwarded to the non-blocked spanning tree links to find the MAC address in the network.