International Business Machines Corporation

Jpmorgan Chase Bank, N.a.

Richard Chen

Marco Pistoia

Antonio Mezzacapo

Jay Michael Gambetta

Quanfu Fan

Shaohan Hu

Don Greenberg

Thomas S Brugler

Randall Avery Craig

Peng Liu

Kristin S Moore

Taylor J Anderson

Giacomo Nannicini

Stephen Peter Wood

Ali Javadiabhari

Rameswar Panda

John A Gunnels

Sijia Liu

Julia Elizabeth Rice

Ivano Tavernelli

Zhonghao Shi

Rogerio Schmidt Feris

Anthony J Annunziata

Lior Horesh

Toyotaro Suzumura

Rudy Raymond Harry Putra

Nikolaj Moll

Dario Gil

Sergey Bravyi

Panagiotis Barkoutsos

Pauline Ollitrault

William R Moriarty

Wei-Cheng Huang

Hsiang Hsu

Hildegard Kuehne

Kanav Setia

One embodiment of the invention provides a method for video recognition. The method comprises receiving an input video comprising a sequence of video segments over a plurality of data modalities. The method further comprises, for a video segment of the sequence, selecting one or more data modalities based on data representing the video segment. Each data modality selected is optimal for video recognition of the video segment. The method further comprises, for each data modality selected, providing at least one data input representing the video segment over the data modality selected to a machine learning model corresponding to the data modality selected, and generating a first type of prediction representative of the video segment via the machine learning model. The method further comprises determining a second type of prediction representative of the entire input video by aggregating all first type of predictions generated.

Adaptive selection of data modalities for efficient video recognition

A method may include: receiving an original dataset and a sensitive attribute; initializing a distilled dataset from the original dataset; initializing a classification model; sampling original dataset data and an original dataset label from the original dataset, and distilled dataset data and a distilled dataset label from the distilled dataset; providing the sampled original dataset data from the original dataset to the classification model, resulting in an original dataset prediction probability; providing the sampled distilled dataset data from the distilled dataset to the classification model, resulting in a distilled dataset prediction probability; calculating a distilled dataset cross-entropy loss for the distilled dataset prediction probability and the distilled dataset label; calculating distilled dataset gradients for the distilled dataset cross-entropy loss; calculating a distance between the gradients as a matching loss; and updating the distilled dataset with the matching loss.

Systems and methods for fairness-aware data distillation for attribute classification

A method for removing uninterested attributes from multi-modality data may include: receiving, by a multi-modality attribute removal computer program executed by an electronic device, multi-modality data comprising a plurality of modalities from a data source, wherein data in each modality are related; receiving, by the multi-modality attribute removal computer program, an uninterested attribute in the multi-modality data to remove; training, by the multi-modality attribute removal computer program, a modality-focused encoder for each modality of the multi-modality data to remove the uninterested attribute using a removal loss and a retention loss for the respective modality; receiving, by the multi-modality attribute removal computer program, a multi-modality data set for processing; and processing, by the multi-modality attribute removal computer program, the multi-modality data set using the modality-focused encoders, wherein the processing results in a processed multi-modality data set with the uninterested attribute removed and one or more interested attribute retained.

Systems and methods for removal of attributes from multi-modality and multi-attribute data

A hybrid classical-quantum computing device to execute a quantum circuit corresponding to a variational problem, is configured. The configuring further comprises causing the hybrid classical-quantum computing device to execute the quantum circuit by performing an adiabatic progression operation, wherein the adiabatic progression operation comprises increasing the difficulty of the variational problem from a simplified version of the problem to the variational problem.

Adiabatic progression with intermediate re-optimization to solve hard variational quantum problems in quantum computing

Techniques and apparatus for analyzing visual content using a visual transformer are described. An example technique includes generating a first set of tokens based on a visual content item. Each token in the first set of tokens is associated with a regional feature from a different region of a plurality of regions of the visual content item. A second set of tokens is generated based on the visual content item. Each token in the second set of tokens is associated with a local feature from one of the plurality of regions of the visual content item. At least one feature map is generated for the visual content item, based on analyzing the first set of tokens and the second set of tokens separately using a hierarchical vision transformer. At least one vision task is performed based on the at least one feature map.

Regional-to-local attention for vision transformers

Systems and techniques that facilitate precision-preserving qubit reduction based on spatial symmetries in fermionic systems are provided. In one or more embodiments, a symmetry component can generate a diagonalized second quantization representation of a spatial point group symmetry operation. The spatial point group symmetry operation can be associated with a molecule (e.g., a geometrical rotation, reflection, and/or inversion of a physical molecule that results in a new molecular orientation that is substantially the same as the original molecular orientation). In one or more embodiments, a transformation component can convert the diagonalized second quantization representation into a single Pauli string. In one or more embodiments, a tapering component can taper off qubits in a computational quantum algorithm that models properties of the molecule, based on the single Pauli string. Various embodiments can thus leverage geometrical spatial symmetries of a molecule to reduce a number of qubits needed to simulate the molecule.

Precision-preserving qubit reduction based on spatial symmetries in fermionic systems

A hybrid-distance adversarial patch generator can be trained to generate a hybrid adversarial patch effective at multiple distances. The hybrid patch can be inserted into multiple sample images, each depicting an object, to simulate inclusion of the hybrid patch at multiple distances. The multiple sample images can then be used to train an object detection model to detect the objects.

Detecting hybdrid-distance adversarial patches

Techniques regarding an iterative energy-scaled variational quantum eigensolver process are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a read-out component that determines a ground state energy value of a quantum Hamiltonian by employing a variational quantum eigensolver (VQE) algorithm, wherein VQE algorithm utilizes a symmetry that emerges at an energy scale of the quantum Hamiltonian.

Iterative energy-scaled variational quantum eigensolver

A method includes detecting submission of a first quantum circuit for compilation, the first quantum circuit comprising a first set of quantum logic gates; generating a first gate index, the first gate index comprising an ordered table of a subset of the set of quantum logic gates, each quantum logic gate of the subset of quantum logic gates including a corresponding set of qubits acted on by the quantum logic gate; comparing the first gate index with a second gate index to determine a structural equality of the first quantum circuit and the second quantum circuit; and parameterizing, in response to determining a structural equality of the first quantum circuit and the second quantum circuit, a first set of parameters of a second set of quantum logic gates of the second quantum circuit with a second set of parameters of the first set of quantum logic gates.

Incremental generation of quantum circuits

From a quantum program a first mutant is generated using a processor and a memory, where the first mutant is a randomly-generated transformation of the quantum program. A quality score, a correctness distance, and a probability of acceptance corresponding to the first mutant are computed. An acceptance corresponding to the first mutant is determined according to the probability of acceptance. Upon determining that an acceptance of the first mutant corresponding to the probability of acceptance exceeds an acceptance threshold, the quantum program is replaced with the first mutant. Upon determining that the quality score exceeds a storage threshold and that the correctness distance is zero, the first mutant is stored. These actions are iterated until reaching an iteration limit.

Monte Carlo Markov chain based quantum program optimization

Embodiments of the present invention are directed to a computer-implemented method for multiscale representation of input data. A non-limiting example of the computer-implemented method includes a processor receiving an original input. The processor downsamples the original input into a downscaled input. The processor runs a first convolutional neural network ('CNN') on the downscaled input. The processor runs a second CNN on the original input, where the second CNN has fewer layers than the first CNN. The processor merges the output of the first CNN with the output of the second CNN and provides a result following the merging of the outputs.

Multiscale feature representations for object recognition and detection

In one or more embodiments described herein, device, computer-implemented methods, and/or computer program products that facilitate automated survey results generation from an image are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an image capturing component that captures a first sample image. The computer executable components can further comprise an image processing component that processes the first sample image to determine a survey count, wherein the survey count indicates a number of times a survey image was identified in the first sample image. The computer executable components can further comprise an authentication component that adjusts the survey count based on detection of a discrepancy.

Automated survey results generation from an image

Techniques regarding quantum computation of molecular excited states are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can categorize a plurality of excited operators from a mapped qubit Hamiltonian into sectors based on a commutation property of the plurality of excited operators with a symmetry from the mapped qubit Hamiltonian. The computer executable components can also comprise a matrix component that can generate an equation of motion matrix from an excited operator from the plurality of excited operators based on the sectors categorized by the initialization component.

Quantum computation of molecular excited states in the presence of Hamiltonian symmetries

A method for bootstrapping a variational algorithm for quantum computing includes performing, using a quantum processor, a first iteration of a variational algorithm on a first wavefunction to compute a first expectation value of a first quantum system corresponding to a solution of the first iteration, the first wavefunction corresponding to a first quantum state of the first quantum system, the first expectation value comprising an energy of the first quantum state. The embodiment includes generating, based on the solution of the first iteration a second wavefunction as output of the first iteration of the variational algorithm, the second wavefunction corresponding to a second quantum state of the first quantum system. The embodiment includes performing, using the quantum processor, a second iteration of the variational algorithm on the second wavefunction to compute a second expectation value of a second quantum system, the second expectation value comprising an energy of a first quantum state of the second quantum system.

Growing community of inventors

Mount Kisco, NY, United States of America

Richard Chen