[go: up one dir, main page]

Lu et al., 2022 - Google Patents

Frozen pretrained transformers as universal computation engines

Lu et al., 2022

View PDF
Document ID
17880037628825399557
Author
Lu K
Grover A
Abbeel P
Mordatch I
Publication year
Publication venue
Proceedings of the AAAI conference on artificial intelligence

External Links

Snippet

We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning--in particular, without finetuning of the self- attention and feedforward layers of the residual blocks. We consider such a model, which we …
Continue reading at ojs.aaai.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6267—Classification techniques
    • G06K9/6268—Classification techniques relating to the classification paradigm, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6217—Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06K9/6232—Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods
    • G06K9/6247—Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods based on an approximation criterion, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G06N3/0635—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means using analogue means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36—Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46—Extraction of features or characteristics of the image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F19/00—Digital computing or data processing equipment or methods, specially adapted for specific applications
    • G06F19/10—Bioinformatics, i.e. methods or systems for genetic or protein-related data processing in computational molecular biology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis

Similar Documents

Publication Publication Date Title
Lu et al. Frozen pretrained transformers as universal computation engines
Gao et al. Adamixer: A fast-converging query-based object detector
Sarwar et al. Gabor filter assisted energy efficient fast learning convolutional neural networks
Khalil et al. Designing novel AAD pooling in hardware for a convolutional neural network accelerator
Pu et al. Fine-grained recognition with learnable semantic data augmentation
Venugopalan et al. Applying deep neural networks for the automatic recognition of sign language words: A communication aid to deaf agriculturists
US20220036231A1 (en) Method and device for processing quantum data
Chen et al. Learning linear regression via single-convolutional layer for visual object tracking
Nie et al. A multi-stage convolution machine with scaling and dilation for human pose estimation
Wu et al. An economic framework for 6-dof grasp detection
Zhang et al. SiT-MLP: A simple MLP with point-wise topology feature learning for skeleton-based action recognition
Chen et al. Deep data augmentation for weed recognition enhancement: A diffusion probabilistic model and transfer learning based approach
Hu et al. Demystify transformers & convolutions in modern image deep networks
Cao et al. Ghostvit: Expediting vision transformers via cheap operations
Jin et al. Groupwise label enhancement broad learning system for image classification
Qiu et al. Semantic-visual guided transformer for few-shot class-incremental learning
Mai et al. From efficient multimodal models to world models: A survey
Hossain et al. Convolutional neural network based skin cancer detection (Malignant vs Benign)
Zand et al. Flow-based spatio-temporal structured prediction of motion dynamics
Dumortier et al. Petribert: Augmenting bert with tridimensional encoding for inverse protein folding and design
Zhou et al. Training-free transformer architecture search with zero-cost proxy guided evolution
Zhang et al. Bidirectional parallel feature pyramid network for object detection
Zahidi et al. Active learning for crop-weed discrimination by image classification from convolutional neural network’s feature pyramid levels
Im et al. Blend AutoAugment: Automatic Data Augmentation for Image Classification Using Linear Blending
Dehban et al. Learning deep features for robotic inference from physical interactions