3.3 Traps and InterruptsTraps, like system calls, occur synchronously for a process. Traps normally occur because of unintentional errors, such as division by zero or indirection through an invalid pointer. The process becomes aware of the problem either by catching a signal or by being terminated. Traps can also occur because of a page fault, in which case the system makes the page available an..

Deep L-layer Neural Network input dim 만큼 input 노드의 수 1개의 input image에 대해, feature들의 수로 해석할 수 있다 Forward Propagation in a Deep Network 모든 training example m개를 한 번에 horizontally 표현하는 것 -> vector version Getting your Matrix Dimensions Right Why Deep Representations? input layer에 가까운 노드들은 엣지 detect (가로, 세로 방향의 low level features) 가운데 - 눈, 코 detect 마지막 - 얼굴 인식 (high level features) 오디오 인식의 경우에도, low ..

Neural Networks Overview Neural Network Representation Computing a Neural Network's Output Vectorizing Across Multiple Examples