Patents by Inventor Serkan Cabi
Serkan Cabi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240042600Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.Type: ApplicationFiled: June 8, 2023Publication date: February 8, 2024Inventors: Serkan Cabi, Ziyu Wang, Alexander Novikov, Ksenia Konyushkova, Sergio Gomez Colmenarejo, Scott Ellison Reed, Misha Man Ray Denil, Jonathan Karl Scholz, Oleg O. Sushkov, Rae Chan Jeong, David Barker, David Budden, Mel Vecerik, Yusuf Aytar, Joao Ferdinando Gomes de Freitas
-
Patent number: 11712799Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.Type: GrantFiled: September 14, 2020Date of Patent: August 1, 2023Assignee: DeepMind Technologies LimitedInventors: Serkan Cabi, Ziyu Wang, Alexander Novikov, Ksenia Konyushkova, Sergio Gomez Colmenarejo, Scott Ellison Reed, Misha Man Ray Denil, Jonathan Karl Scholz, Oleg O. Sushkov, Rae Chan Jeong, David Barker, David Budden, Mel Vecerik, Yusuf Aytar, Joao Ferdinando Gomes de Freitas
-
Publication number: 20220261639Abstract: A method is proposed of training a neural network to generate action data for controlling an agent to perform a task in an environment. The method includes obtaining, for each of a plurality of performances of the task, one or more first tuple datasets, each first tuple dataset comprising state data characterizing a state of the environment at a corresponding time during the performance of the task; and a concurrent process of training the neural network and a discriminator network. The training process comprises a plurality of neural network update steps and a plurality of discriminator network update steps.Type: ApplicationFiled: July 16, 2020Publication date: August 18, 2022Inventors: Konrad Zolna, Scott Ellison Reed, Ziyu Wang, Alexander Novikov, Sergio Gomez Colmenarejo, Joao Ferdinando Gomes de Freitas, David Budden, Serkan Cabi
-
Publication number: 20210078169Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.Type: ApplicationFiled: September 14, 2020Publication date: March 18, 2021Inventors: Serkan Cabi, Ziyu Wang, Alexander Novikov, Ksenia Konyushkova, Sergio Gomez Colmenarejo, Scott Ellison Reed, Misha Man Ray Denil, Jonathan Karl Scholz, Oleg O. Sushkov, Rae Chan Jeong, David Barker, David Budden, Mel Vecerik, Yusuf Aytar, Joao Ferdinando Gomes de Freitas
-
Publication number: 20200167633Abstract: A reinforcement learning system is proposed comprising a plurality of property detector neural networks. Each property detector neural network is arranged to receive data representing an object within an environment, and to generate property data associated with a property of the object. A processor is arranged to receive an instruction indicating a task associated with an object having an associated property, and process the output of the plurality of property detector neural networks based upon the instruction to generate a relevance data item. The relevance data item indicates objects within the environment associated with the task. The processor also generates a plurality of weights based upon the relevance data item, and, based on the weights, generates modified data representing the plurality of objects within the environment. A neural network is arranged to receive the modified data and to output an action associated with the task.Type: ApplicationFiled: May 22, 2018Publication date: May 28, 2020Inventors: Misha Man Ray Denil, Sergio Gomez Colmenarejo, Serkan Cabi, David William Saxton, Joao Ferdinando Gomes de Freitas
-
Publication number: 20180185314Abstract: Pentacyclic triterpene weight loss agents are provided herein. Also provided are pharmaceutical formulations containing a therapeutically effective amount of one or more of the weight loss agents, or pharmaceutically acceptable salts or prodrugs thereof, in combination with one or more pharmaceutically acceptable excipients. The pharmaceutical formulations can be administered to a pre-obese, obese, or morbidly obese patient to induce weight loss, reduce body fat, reduce food intake, improve glucose homeostasis, prevent obesity, or a combination thereof. The weight loss agents can also be co-administered with leptin or a leptin analog.Type: ApplicationFiled: February 28, 2018Publication date: July 5, 2018Inventors: Umut Ozcan, Joseph Majzoub, Ralph Mazitschek, Isin Cakir, Serkan Cabi
-
Patent number: 9968575Abstract: Pentacyclic triterpene weight loss agents are provided herein. Also provided are pharmaceutical formulations containing a therapeutically effective amount of one or more of the weight loss agents, or pharmaceutically acceptable salts or prodrugs thereof, in combination with one or more pharmaceutically acceptable excipients. The pharmaceutical formulations can be administered to a pre-obese, obese, or morbidly obese patient to induce weight loss, reduce body fat, reduce food intake, improve glucose homeostasis, prevent obesity, or a combination thereof. The weight loss agents can also be co-administered with leptin or a leptin analog.Type: GrantFiled: September 26, 2013Date of Patent: May 15, 2018Assignees: The Children's Medical Center Corporation, The General Hospital CorporationInventors: Umut Ozcan, Joseph Majzoub, Ralph Mazitschek, Isin Cakir, Serkan Cabi
-
Patent number: 9925161Abstract: Pentacyclic triterpene weight loss agents are provided herein. Also provided are pharmaceutical formulations containing a therapeutically effective amount of one or more of the weight loss agents, or pharmaceutically acceptable salts or prodrugs thereof, in combination with one or more pharmaceutically acceptable excipients. The pharmaceutical formulations can be administered to a pre-obese, obese, or morbidly obese patient to induce weight loss, reduce body fat, reduce food intake, improve glucose homeostasis, prevent obesity, or a combination thereof. The weight loss agents can also be co-administered with leptin or a leptin analog.Type: GrantFiled: July 7, 2017Date of Patent: March 27, 2018Assignees: The Children's Medical Center Corporation, The General Hospital CorporationInventors: Umut Ozcan, Joseph Majzoub, Ralph Mazitschek, Isin Cakir, Serkan Cabi
-
Publication number: 20170304245Abstract: Pentacyclic triterpene weight loss agents are provided herein. Also provided are pharmaceutical formulations containing a therapeutically effective amount of one or more of the weight loss agents, or pharmaceutically acceptable salts or prodrugs thereof, in combination with one or more pharmaceutically acceptable excipients. The pharmaceutical formulations can be administered to a pre-obese, obese, or morbidly obese patient to induce weight loss, reduce body fat, reduce food intake, improve glucose homeostasis, prevent obesity, or a combination thereof. The weight loss agents can also be co-administered with leptin or a leptin analog.Type: ApplicationFiled: July 7, 2017Publication date: October 26, 2017Inventors: Umut Ozcan, Joseph Majzoub, Ralph Mazitschek, Isin Cakir, Serkan Cabi
-
Publication number: 20170209408Abstract: HSP 90 inhibitors for the promotion of weight loss, as well as formulations containing these inhibitors and methods of using thereof, are described herein. Also provided are pharmaceutical compositions containing a therapeutically effective amount of a weight loss agent, or a pharmaceutically acceptable salt or prodrug thereof, in combination with one or more pharmaceutically acceptable excipients. The pharmaceutical compositions can be administered to induce weight loss in a pre-obese, obese, or morbidly obese patient, reduce body fat in a pre-obese, obese, or morbidly obese patient, reduce food intake in a pre-obese, obese, or morbidly obese patient, improve glucose homeostasis in a pre-obese, obese, or morbidly obese patient, or combinations thereof. In particular embodiments, the weight loss agent is co-administered with leptin or a leptin analog.Type: ApplicationFiled: April 3, 2015Publication date: July 27, 2017Inventors: Umut Özcan, Isin Cakir, Serkan Cabi
-
Publication number: 20150250753Abstract: Pentacyclic triterpene weight loss agents are provided herein. Also provided are pharmaceutical formulations containing a therapeutically effective amount of one or more of the weight loss agents, or pharmaceutically acceptable salts or prodrugs thereof, in combination with one or more pharmaceutically acceptable excipients. The pharmaceutical formulations can be administered to a pre-obese, obese, or morbidly obese patient to induce weight loss, reduce body fat, reduce food intake, improve glucose homeostasis, prevent obesity, or a combination thereof. The weight loss agents can also be co-administered with leptin or a leptin analog.Type: ApplicationFiled: September 26, 2013Publication date: September 10, 2015Inventors: Umut Ozcan, Joseph Majzoub, Ralph Mazitschek, Isin Cakir, Serkan Cabi