[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f6LQIQ5aZyoyEjJcFET-GOFDOPBc6dQFjl00ebrXpuFE":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":18,"related":19,"source":29,"type":30},[],"2023-06-03 13:36:45",43644234,[8,9,10,11],"弱化学习","强化学习","监督学习","非监督学习",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":16},85,"306d47969b59e6f36470c235ae597dac","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F151b1e04e0edd24518d87450e76e122a.jpg","人工智能与信息社会","exam_89862912","在自动驾驶中,AI需要不断地通过路面信息来调整开车的决策,这种处理模式适合用()来训练出合理的策略",[20,31,40,49,58,61,70,79,88,97],{"answer":21,"createTime":5,"id":22,"options":23,"question":28,"source":29,"type":30},[],43644230,[24,25,26,27],"梯度下降","反向传播","优化函数","损失函数","()是用来评估神经网络的计算模型对样本的预测值和真实值之间的误差大小","v1",0,{"answer":32,"createTime":5,"id":33,"options":34,"question":39,"source":29,"type":30},[],43644231,[35,36,37,38],"输出","开发","探索","输入","强化学习中,()主要探索未知的动作会产生的效果,有利于更新Q值,获得更好的策略",{"answer":41,"createTime":5,"id":42,"options":43,"question":48,"source":29,"type":30},[],43644232,[44,45,46,47],"大;小","小;小","小;大","大;大","在强化学习的过程中,学习率α越大,表示采用新的尝试得到的结果比例越(),保持旧的结果的比例越()",{"answer":50,"createTime":5,"id":51,"options":52,"question":57,"source":29,"type":30},[],43644233,[53,54,55,56],"当前状态","主体内因","历史状态","外部影响","马尔可夫性质强调在每一个动作状态序列中,下一个状态与()有关",{"answer":59,"createTime":5,"id":6,"options":60,"question":18,"source":29,"type":30},[],[8,9,10,11],{"answer":62,"createTime":5,"id":63,"options":64,"question":69,"source":29,"type":30},[],43644235,[65,66,67,68],"知识库变大","推理引擎更加专用","用户接口更多样","用户需求量减少","专家系统的发展趋势不包括()",{"answer":71,"createTime":5,"id":72,"options":73,"question":78,"source":29,"type":30},[],43644236,[74,75,76,77],"Mo Go","GNU Go","Alpha Go","DeepZen Go","围棋AI()是基于AlphaBeta剪枝算法的",{"answer":80,"createTime":5,"id":81,"options":82,"question":87,"source":29,"type":30},[],43644237,[83,84,85,86],".红、黄、蓝","黄、绿、蓝","红、绿、黄","红、绿、蓝","色彩的三原色模型是()",{"answer":89,"createTime":5,"id":90,"options":91,"question":96,"source":29,"type":30},[],43644238,[92,93,94,95],"语音识别","自动驾驶","情感计算","医学影像分析","科大讯飞目前的主要业务领域是()",{"answer":98,"createTime":5,"id":99,"options":100,"question":105,"source":29,"type":30},[],43644239,[101,102,103,104],"PROSPECTOR","DENDRAL","MYCIN","XCON","1977年在斯坦福大学研发的专家系统()是用于地质领域探测矿藏的一个专家系统"]