Optimizing Image Classification: Automated Deep Learning Architecture Crafting with Network and Learning Hyperparameter Tuning

. 2023 Nov 4;8(7):525. doi: 10.3390/biomimetics8070525

Algorithm 5: Stochastic Peer Interaction in ETLBOCBL-CNN’s Modified Teacher Phase
Inputs: $N$ , $D$ , $P^{o f f} = [X_{1}^{o f f}, \dots, X_{n}^{o f f}, \dots ., X_{N}^{o f f}]$ , $X^{T e a c h e r}$ , $ℛ^{t r a i n}$ , $ℛ^{v a l i d}$ , $S^{b a t c h}$ , $ε^{t r a i n}$ , $R^{L}$ , $C^{n u m}$
01:	Initialize clone population set as $P^{c l o n e} \leftarrow \emptyset$ ;
02:	Construct $P^{c l o n e}$ by duplicating $P^{o f f}$ and sorting the offspring learners ascendingly by referring to their fitness values of $X_{n}^{c l o n e} . E r r$ for $n = 1, \dots, N$ ;
03:	Construct $P^{T 20}$ and $P^{T 50}$ by extracting the top 20% and 50% of offspring learners stored in $P^{c l o n e}$ ;
04:	for $n = 1$ to $N$ do
05:	for $d = 1$ to D do
06:	Randomly generate $r a n d \in [0, 1]$ from uniform distribution;
07:	if $0 \leq r a n d < 1 / 3$ then
08:	Randomly select $X_{p}^{T 20}$ and $X_{q}^{T 20}$ from $P^{T 20}$ , where $p \neq q \neq n$ ;
09:	Update $X_{n}^{o f f} . {P o s}_{d}$ using Equation (14);
10:	else if $1 / 3 \leq r a n d < 2 / 3$ then
11:	Randomly select $X_{r}^{T 50}$ from $P^{T 50}$ , where $r \neq n$ ;
12:	Update $X_{n}^{o f f} . {P o s}_{d}$ using Equation (15);
13:	else if $2 / 3 \leq r a n d \leq 1$ then
14:	Retain the original value of $X_{n}^{o f f} . {P o s}_{d}$ ;
15:	end if
16:	if $d \neq 2 N_{m a x}^{C o n v} + 3 l - 1$ with $l = 1, \dots, N_{m a x}^{C o n v}$ then
17:	$X_{n}^{o f f} . {P o s}_{d} \leftarrow R o u n d (X_{n}^{o f f} . P o s_{d})$ ;
18:	end if
19:	end for
20:	Perform fitness evaluation on the updated $X_{n}^{o f f} . P o s$ to obtain new $X_{n}^{o f f} . E r r$ using Algorithm 2;
21:	if $X_{n}^{o f f} . E r r < X^{T e a c h e r} . E r r$ then
22:	$X^{T e a c h e r} . P o s \leftarrow X_{n}^{o f f} . P o s$ , $X^{T e a c h e r} . E r r \leftarrow X_{n}^{o f f} . E r r$ ;
23:	end if
24:	end for
Output: Updated $P^{o f f} = [X_{1}^{o f f}, \dots, X_{n}^{o f f}, \dots ., X_{N}^{o f f}]$ and $X^{T e a c h e r}$