Unverified50% confidenceFactExact time
Samuel's program used minimax search for forward lookahead and employed an early form of alpha-beta pruning to reduce the search space.
1
Sources
50%
Confidence
Long-term
Relevance
8/16/2026
First Seen
Sources
塞缪尔跳棋程序：机器学习的真正起点
Related Claims
Unverified该方案选用小而快的检索模型，重建索引不到一秒，属于选择速度而非完美的权衡63% similarUnverifiedRAG依赖精确的向量检索推理成本低但受限于检索质量，超长上下文窗口避免检索失配但KV缓存显存占用随上下文长度线性增长导致推理延迟和成本上升60% similarUnverified将进化搜索限制在球面流形上理论上可将有效搜索空间体积压缩数个数量级，从而部分抵消高维空间的样本效率损失60% similarUnverifiedBeginners should adopt a learn-as-you-go strategy, deeply understanding derivatives only when encountering algorithms that use gradient descent.60% similarUnverifiedIVF算法通过K-means聚类将向量空间分区，检索时只扫描最近的若干分区，以牺牲少量精度换取更低的内存占用59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/758710API
curl https://kongchang.com/api/v1/knowledge/claims/758710MCP
get_claim(id=758710)