In this lecture, we complete our discussion of how backpropagation allows for gradient descent to train deep neural networks (feed-forward, multi-layer perceptrons in general). We then pivot to talking about more regularized feed-forward neural networks, like convolutional neural networks (CNNs) that combine convolutional layers with pooling layers and thereby simplify training while producing a low-dimensional feature set (relative to the dimensions of the input). After a brief discussion of the feed-forward architecture of the insect/pancrustacean brain, we shift to discussing time-delay neural networks (TDNNs) as an entry point into discussing recurrent neural networks (RNNs) and reservoir machines, which we will pick up on next time.
Archived lectures from graduate course on nature-inspired metaheuristics given at Arizona State University by Ted Pavlic
Tuesday, April 5, 2022
Lecture 7D (2022-04-05): CNNs, Insect Brains, More Complex Neural Networks (TDNNs and RNNs)
Subscribe to:
Post Comments (Atom)
Popular Posts
-
This 20-minute segment provides an overview of the format and expectations for the final exam for the Spring 2022 section of IEE/CSE 598 (Bi...
-
In this lecture, we start with an outline of the Metropolis–Hastings (MH) Markov Chain Monte Carlo (MCMC) sampling algorithm and describe h...
-
In this lecture, we continue to discuss nature-inspired algorithms that come from the non-biological, physics realm. Maximum entropy (MaxEn...
-
Today's lecture introduces the course, its structures, and its policies. Then a basic introduction to metaheuristics is given, leading ...
-
In this first lecture of the semester, I introduce the course and its expectations and policies. After highlighting several sections of the ...
-
This lecture closes out our discussion of the basic Genetic Algorithm (GA) and introduces closely related approaches for problems not direc...
-
The prototypical structure of evolutionary algorithms are presented, along with the background context of direct search metaheuristics (inc...
-
In this lecture, we introduce thinking about computation from a complex systems perspective. This transition is motivated by thinking about...
-
In this lecture, we introduce a short unit on complex systems approaches that intersect with computation and algorithms. We start with Inter...
-
In this lecture, we review Elementary Cellular Automata (ECA's) and some classic rules and how to interpret them. We then transition to ...
No comments:
Post a Comment