多类支持向量机损失(SVM损失)

(SVM) 损失。SVM 损失的设置是,SVM"希望"每个图像的正确类别的得分比错误类别高出一定幅度Δ。

即假设有一个分数集合s=[13,−7,11]

如果y0为真实值,超参数为10,则该损失值为

超参数是指在机器学习算法的训练过程中需要设置的参数,它们不同于模型本身的参数(例如权重和偏置),是需要在训练之前预先确定的。超参数在模型训练和性能优化中起着关键作用。

正则化

c 复制代码
def L_i(x, y, W):
  """
  unvectorized version. Compute the multiclass svm loss for a single example (x,y)
  - x is a column vector representing an image (e.g. 3073 x 1 in CIFAR-10)
    with an appended bias dimension in the 3073-rd position (i.e. bias trick)
  - y is an integer giving index of correct class (e.g. between 0 and 9 in CIFAR-10)
  - W is the weight matrix (e.g. 10 x 3073 in CIFAR-10)
  """
  delta = 1.0 # see notes about delta later in this section
  scores = W.dot(x) # scores becomes of size 10 x 1, the scores for each class
  correct_class_score = scores[y]
  D = W.shape[0] # number of classes, e.g. 10
  loss_i = 0.0
  for j in range(D): # iterate over all wrong classes
    if j == y:
      # skip for the true class to only loop over incorrect classes
      continue
    # accumulate loss for the i-th example
    loss_i += max(0, scores[j] - correct_class_score + delta)
  return loss_i

def L_i_vectorized(x, y, W):
  """
  A faster half-vectorized implementation. half-vectorized
  refers to the fact that for a single example the implementation contains
  no for loops, but there is still one loop over the examples (outside this function)
  """
  delta = 1.0
  scores = W.dot(x)
  # compute the margins for all classes in one vector operation
  margins = np.maximum(0, scores - scores[y] + delta)
  # on y-th position scores[y] - scores[y] canceled and gave delta. We want
  # to ignore the y-th position and only consider margin on max wrong class
  margins[y] = 0
  loss_i = np.sum(margins)
  return loss_i

def L(X, y, W):
  """
  fully-vectorized implementation :
  - X holds all the training examples as columns (e.g. 3073 x 50,000 in CIFAR-10)
  - y is array of integers specifying correct class (e.g. 50,000-D array)
  - W are weights (e.g. 10 x 3073)
  """
  # evaluate loss over all examples in X without using any for loops
  # left as exercise to reader in the assignment
相关推荐
音视频牛哥12 分钟前
视觉系统的秩序:从滤波、边缘检测到形态学操作
opencv·机器学习·计算机视觉
OG one.Z17 分钟前
08_集成学习
人工智能·算法·机器学习
CoovallyAIHub34 分钟前
超越传统3D生成:OccScene实现感知与生成的跨任务共赢
深度学习·算法·计算机视觉
Mr.H012743 分钟前
克鲁斯卡尔(Kruskal)算法
数据结构·算法·图论
Tisfy44 分钟前
LeetCode 3346.执行操作后元素的最高频率 I:滑动窗口(正好适合本题数据,II再另某他法)
算法·leetcode·题解·滑动窗口·哈希表
CoovallyAIHub1 小时前
华为世界模型来了!30分钟生成272㎡室内场景,虚拟人导航不迷路
深度学习·算法·计算机视觉
熬了夜的程序员1 小时前
【LeetCode】94. 二叉树的中序遍历
数据结构·算法·leetcode·职场和发展·深度优先
剑指~巅峰1 小时前
Rust智能指针的奇妙之旅:从踩坑到顿悟
开发语言·人工智能·深度学习·机器学习·rust
放羊郎1 小时前
SLAM各类算法特点对比
人工智能·算法·slam·视觉slam·建图·激光slam
熬了夜的程序员1 小时前
【LeetCode】92. 反转链表 II
数据结构·算法·leetcode·链表·职场和发展·排序算法