Homework Help is Here – Start Your Trial Now!
Engineering
Computer Engineering
RNN CNN Self-attention ఆరో Fig. 10.6.1: Comparing CNN (padding tokens are omitted), RNN, and self-attention architectures. Consider a convolutional layer whose kernel size is k. We will provide more details about sequence processing using CNNS in later chapters. For now, we only need to know that since the sequence length is n, the numbers of input and output channels are both d, the computational complexity of the convolutional layer is O(knd²). As Fig. 10.6.1 shows, CNNs are hierarchical so there are O(1) sequential operations and the maximum path length is O(n/k). For example, x1 and x5 are within the receptive field of a two-layer CNN with kernel size 3 in Fig. 10.6.1. When updating the hidden state of RNNS, multiplication of the d x d weight matrix and the d- dimensional hidden state has a computational complexity of O(d²). Since the sequence length is n, the computational complexity of the recurrent layer is O(nd2). According to Fig. 10.6.1, there are O(n) sequential operations that cannot be parallelized and the maximum path length is also O(n).

RNN CNN Self-attention ఆరో Fig. 10.6.1: Comparing CNN (padding tokens are omitted), RNN, and self-attention architectures. Consider a convolutional layer whose kernel size is k. We will provide more details about sequence processing using CNNS in later chapters. For now, we only need to know that since the sequence length is n, the numbers of input and output channels are both d, the computational complexity of the convolutional layer is O(knd²). As Fig. 10.6.1 shows, CNNs are hierarchical so there are O(1) sequential operations and the maximum path length is O(n/k). For example, x1 and x5 are within the receptive field of a two-layer CNN with kernel size 3 in Fig. 10.6.1. When updating the hidden state of RNNS, multiplication of the d x d weight matrix and the d- dimensional hidden state has a computational complexity of O(d²). Since the sequence length is n, the computational complexity of the recurrent layer is O(nd2). According to Fig. 10.6.1, there are O(n) sequential operations that cannot be parallelized and the maximum path length is also O(n).

Computer Networking: A Top-Down Approach (7th Edition)
Computer Networking: A Top-Down Approach (7th Edition)
7th Edition
ISBN:9780133594140
Author:James Kurose, Keith Ross
Publisher:James Kurose, Keith Ross
Chapter1: Computer Networks And The Internet
Section: Chapter Questions
Problem R1RQ: What is the difference between a host and an end system? List several different types of end...
See similar textbooks
icon
Related questions
Question
Answer in programming language
RNN CNN Self-attention 000% ఆరోరోం Fig. 10.6.1: Comparing CNN (padding tokens are omitted), RNN, and self-attention architectures. Consider a convolutional layer whose kernel size is k. We will provide more details about sequence processing using CNNS in later chapters. For now, we only need to know that since the sequence length is n, the numbers of input and output channels are both d, the computational complexity of the convolutional layer is O(kd²). As Fig. 10.6.1 shows, CNNs are hierarchical so there are O(1) sequential operations and the maximum path length is O(n/k). For example, x1 and x5 are within the receptive field of a two-layer CNN with kernel size 3 in Fig. 10.6.1. When updating the hidden state of RNNS, multiplication of the d x d weight matrix and the d- dimensional hidden state has a computational complexity of O(d?). Since the sequence length is n, the computational complexity of the recurrent layer is O(nd?). According to Fig. 10.6.1, there are O(n) sequential operations that cannot be parallelized and the maximum path length is also O(n).
Transcribed Image Text:RNN CNN Self-attention 000% ఆరోరోం Fig. 10.6.1: Comparing CNN (padding tokens are omitted), RNN, and self-attention architectures. Consider a convolutional layer whose kernel size is k. We will provide more details about sequence processing using CNNS in later chapters. For now, we only need to know that since the sequence length is n, the numbers of input and output channels are both d, the computational complexity of the convolutional layer is O(kd²). As Fig. 10.6.1 shows, CNNs are hierarchical so there are O(1) sequential operations and the maximum path length is O(n/k). For example, x1 and x5 are within the receptive field of a two-layer CNN with kernel size 3 in Fig. 10.6.1. When updating the hidden state of RNNS, multiplication of the d x d weight matrix and the d- dimensional hidden state has a computational complexity of O(d?). Since the sequence length is n, the computational complexity of the recurrent layer is O(nd?). According to Fig. 10.6.1, there are O(n) sequential operations that cannot be parallelized and the maximum path length is also O(n).
Expert Solution
steps

Step by step

Solved in 2 steps

SEE SOLUTIONCheck out a sample Q&A here
Blurred answer
Recommended textbooks for you
Computer Networking: A Top-Down Approach (7th Edi…
Computer Networking: A Top-Down Approach (7th Edi…
Computer Engineering
ISBN:
9780133594140
Author:
James Kurose, Keith Ross
Publisher:
PEARSON
Computer Organization and Design MIPS Edition, Fi…
Computer Organization and Design MIPS Edition, Fi…
Computer Engineering
ISBN:
9780124077263
Author:
David A. Patterson, John L. Hennessy
Publisher:
Elsevier Science
Network+ Guide to Networks (MindTap Course List)
Network+ Guide to Networks (MindTap Course List)
Computer Engineering
ISBN:
9781337569330
Author:
Jill West, Tamara Dean, Jean Andrews
Publisher:
Cengage Learning
Concepts of Database Management
Concepts of Database Management
Computer Engineering
ISBN:
9781337093422
Author:
Joy L. Starks, Philip J. Pratt, Mary Z. Last
Publisher:
Cengage Learning
Prelude to Programming
Prelude to Programming
Computer Engineering
ISBN:
9780133750423
Author:
VENIT, Stewart
Publisher:
Pearson Education
Sc Business Data Communications and Networking, T…
Sc Business Data Communications and Networking, T…
Computer Engineering
ISBN:
9781119368830
Author:
FITZGERALD
Publisher:
WILEY
SEE MORE TEXTBOOKS