[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f5vM7G7sIOSLCRxkrlJ5Uux03-N10y7nA2ai-clB-Y40":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":13,"question":17,"related":18,"source":26,"type":41},[],"2025-08-29 14:53:51",1069778287,[8,9,10,11,12],"线性回归可以用于预测连续型变量","线性回归模型只适用于线性关系的特征与输出之间","线性回归模型的参数可以通过最小二乘法来估计","线性回归只适用于单变量情况,无法处理多变量问题","线性回归模型的残差应当是独立同分布的",{"courseId":14,"workId":15,"workName":16},"1000128448","61857009","第三章单元测试","在线性回归中,以下哪些说法是正确的",[19,28,38,42,47,56,65,74],{"answer":20,"createTime":5,"id":21,"options":22,"question":25,"source":26,"type":27},[],1069778255,[23,24],"正确","错误","机器学习是人工智能的一个子领域,其主要任务包括分类、回归和聚类等.根据这一描述,机器学习的任务仅限于分类和回归,而聚类不是机器学习的任务","v2",3,{"answer":29,"createTime":5,"id":30,"options":31,"question":36,"source":26,"type":37},[],1069778269,[32,33,34,35],"线性回归模型的损失函数通常使用均方误差(MSE),它是预测值与实际值之间差异的平方和的平均","线性回归模型的损失函数是通过绝对值误差计算的,而不是均方误差(MSE)","使用梯度下降法优化损失函数时,目标是最大化损失,而不是最小化","线性回归模型不需要进行参数优化,可以直接通过公式得到最佳参数","在进行线性回归模型的训练过程中,我们希望通过优化损失函数来找到最佳的模型参数.以下关于线性回归损失函数和优化方法的描述中,哪一项是正确的",0,{"answer":39,"createTime":5,"id":6,"options":40,"question":17,"source":26,"type":41},[],[8,9,10,11,12],1,{"answer":43,"createTime":5,"id":44,"options":45,"question":46,"source":26,"type":27},[],1069778317,[23,24],"逻辑回归是一种用于多分类任务的机器学习模型,能够将线性输出转化为概率,并在多个领域中应用",{"answer":48,"createTime":5,"id":49,"options":50,"question":55,"source":26,"type":41},[],1069778336,[51,52,53,54],"机器学习是人工智能的一个分支","机器学习的主要任务是通过算法实现已知条件X到目标值y的转换","机器学习只适用于大数据环境","机器学习可以用于预测、分类和回归等多种任务","关于机器学习的基本概念,以下哪些描述是正确的",{"answer":57,"createTime":5,"id":58,"options":59,"question":64,"source":26,"type":37},[],1069778344,[60,61,62,63],"衡量模型在训练集上的表现","调整模型的超参数","评估模型的泛化能力","指导模型参数的更新方向","在模型训练过程中,损失函数的主要作用是什么",{"answer":66,"createTime":5,"id":67,"options":68,"question":73,"source":26,"type":37},[],1069778351,[69,70,71,72],"用于衡量模型的复杂度","用于衡量模型预测结果与实际结果之间的差距","用于优化模型参数","用于评估模型的训练时间","在机器学习中,损失函数的主要作用是什么",{"answer":75,"createTime":5,"id":76,"options":77,"question":82,"source":26,"type":37},[],1069778358,[78,79,80,81],"有监督学习需要使用目标值y来训练模型,而无监督学习则不需要","无监督学习比有监督学习更容易实现,通常不需要任何数据预处理","有监督学习主要用于聚类问题,而无监督学习用于分类问题","无监督学习的结果总是比有监督学习的结果更准确","在机器学习中,有监督学习与无监督学习的主要区别在于是否使用目标值y.以下关于这两种学习方式的描述中,哪一项是正确的"]