인공지능 썸네일형 리스트형 Deep Learning using Rectified Linear Units (ReLU) https://arxiv.org/abs/1803.08375 Deep Learning using Rectified Linear Units (ReLU)We introduce the use of rectified linear units (ReLU) as the classification function in a deep neural network (DNN). Conventionally, ReLU is used as an activation function in DNNs, with Softmax function as their classification function. However, there havearxiv.org 요약우리는 심층 신경망(DNN)에서 ReLU(Rectified Linear Unit)를 분.. 더보기 Gaussian Error Linear Units (GELUs) https://arxiv.org/abs/1606.08415 Gaussian Error Linear Units (GELUs)We propose the Gaussian Error Linear Unit (GELU), a high-performing neural network activation function. The GELU activation function is $xΦ(x)$, where $Φ(x)$ the standard Gaussian cumulative distribution function. The GELU nonlinearity weights inputs byarxiv.org 1. 서론초기의 인공 뉴런들은 이진 임계 단위를 사용했습니다(Hopfield, 1982; McCulloch & Pitt.. 더보기 GLU Variants Improve Transformer (SwiGLU) https://arxiv.org/abs/2002.05202 GLU Variants Improve TransformerGated Linear Units (arXiv:1612.08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function. Variations on GLU are possible, using different nonlinear (or even linear) functions in place ofarxiv.org 요약Gated Linear Units (GLU) [Dauphin et al., 2016]는 두 개의 선형 투영(Linea.. 더보기 Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model https://www.arxiv.org/abs/2408.11039 Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal ModelWe introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over mixed-modality sequencarxiv.org 초록우리는 이산 및 연속 .. 더보기 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation https://arxiv.org/abs/1606.06650 3D U-Net: Learning Dense Volumetric Segmentation from Sparse AnnotationThis paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the volume to be segmentarxiv.org 초록이 논문은 희소하게 주석된 볼륨 이미지를 학습하.. 더보기 AudioLDM: Text-to-Audio Generation with Latent Diffusion Models (부록 추가 필요) https://ar5iv.labs.arxiv.org/html/2301.12503 AudioLDM: Text-to-Audio Generation with Latent Diffusion ModelsText-to-audio (TTA) systems have recently gained attention for their ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computatio…ar5iv.labs.arxiv.org 요약텍스트를 기반으로 오디오를 합성하는 텍스트-투-오디오(TTA) 시스템은 최근 들어 많은.. 더보기 ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers https://arxiv.org/abs/2305.15272 ViTMatte: Boosting Image Matting with Pretrained Plain Vision TransformersRecently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image matting. We hypotarxiv.org 요약최근 순수 비전 트랜스포머(ViTs)는 강.. 더보기 Aggregated Residual Transformations for Deep Neural Networks (ResNeXt) https://arxiv.org/abs/1611.05431 Aggregated Residual Transformations for Deep Neural NetworksWe present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, mularxiv.org 초록우리는 이미지 분류를 위한 간단하고 고도로 모듈화된 네트워크 아키텍.. 더보기 이전 1 ··· 6 7 8 9 10 11 12 ··· 22 다음
