相关实验视频
Updated: Jul 13, 2025

06:48
Surface Mapping of Earth-like Exoplanets using Single Point Light Curves
Published on: May 10, 2020
3.6K
通过专家子空间投影进行数据集凝聚.
Zhiheng Ma1, Dezheng Gao2, Shaolei Yang3
1Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
Sensors (Basel, Switzerland)
|October 14, 2023
概括
数据集凝聚通过创建更小的合成数据集来减少大型深度学习数据集. 专家子空间投影 (ESP) 可以有效地实现这一目标,提高性能并降低成本.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 深度学习模型需要大量的数据集,增加存储和培训成本.
- 数据集凝聚旨在创建更小的合成数据集,保持性能.
- 由于梯度展开,现有的轨迹匹配方法在计算上昂贵.
研究的目的:
- 提出一种新的数据集凝聚方法,即专家子空间投影 (ESP).
- 为了减少与轨迹匹配相关的计算和内存开销.
- 以显著更小的数据集来维持下游模型性能.
主要方法:
- 专家子空间投影 (ESP) 限制了真实数据轨迹子空间内的合成数据轨迹.
- 避免复杂的梯度在多个训练代中展开.
- 允许在完整的合成数据集上进行公正的训练.
主要成果:
- ESP显著优于轨迹匹配方法,在CIFAR10 (1图像/类) 上实现了16.7%的改进.
- 拟议的方法比以前的最先进方法高出3.2%.
- ESP提供了节省内存的优势,并与其他凝结技术进行集成.
结论:
- 专家子空间投影 (ESP) 是一种有效的数据集凝聚技术.
- ESP可以降低计算成本,同时保持或提高模型性能.
- 这种方法解决了在深度学习中迫切需要有效减少数据集大小的迫切需要.
相关概念视频
Residuals and Least-Squares Property
7.4K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.4K
Deconvolution
168
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
168
Extraction: Partition and Distribution Coefficients
2.5K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
For extracting a solute from an aqueous phase into an...
2.5K
State Space Representation
216
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
Consider an RLC circuit, a...
216
Fischer Projections
13.3K
Learning to draw Fischer projections of molecules and understanding their relevance plays a crucial role in the visual depiction of organic molecules. A Fischer projection is a two-dimensional projection on a planar surface to simplify the three-dimensional wedge–dash representation of molecules. This is especially helpful in the case of molecules with multiple chiral centers that can be difficult to draw. Here, all the bonds of interest are represented as horizontal or vertical lines.
13.3K
Linear Approximation in Frequency Domain
94
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
94

