
is one factor in frequent between recollections, oscillating chemical reactions and double pendulums? All these programs have a basin of attraction for doable states, like a magnet that attracts the system in direction of sure trajectories. Complicated programs with a number of inputs often evolve over time, producing intricate and generally chaotic behaviors. Attractors symbolize the long-term behavioral sample of dynamical programs — a sample to which a system converges over time no matter its preliminary circumstances.
Neural networks have develop into ubiquitous in our present Synthetic Intelligence period, sometimes serving as highly effective instruments for illustration extraction and sample recognition. Nevertheless, these programs will also be seen by one other fascinating lens: as dynamical programs that evolve and converge to a manifold of states over time. When applied with suggestions loops, even easy neural networks can produce strikingly stunning attractors, starting from restrict cycles to chaotic constructions.
Neural Networks as Dynamical Programs
Whereas neural networks usually sense are mostly identified for embedding extraction duties, they will also be seen as dynamical programs. A dynamical system describes how factors in a state house evolve over time in line with a hard and fast algorithm or forces. Within the context of neural networks, the state house consists of the activation patterns of neurons, and the evolution rule is set by the community’s weights, biases, activation capabilities, and different tips.
Conventional NNs are optimized by way of gradient descent to seek out its endstate of convergence. Nevertheless, after we introduce suggestions — connecting the output again to the enter — the community turns into a recurrent system with a unique type of temporal dynamic. These dynamics can exhibit a variety of behaviors, from easy convergence to a hard and fast level to advanced chaotic patterns.
Understanding Attractors
An attractor is a set of states towards which a system tends to evolve from all kinds of beginning circumstances. As soon as a system reaches an attractor, it stays inside that set of states until perturbed by an exterior pressure. Attractors are certainly deeply concerned in forming recollections [1], oscillating chemical reactions [2], and different nonlinear dynamical programs.
Kinds of Attractors
Dynamical Programs can exhibit a number of varieties of attractors, every with distinct traits:
- Level Attractors: the best kind, the place the system converges to a single fastened level no matter beginning circumstances. This represents a steady equilibrium state.
- Restrict Cycles: the system settles right into a repeating periodic orbit, forming a closed loop in part house. This represents oscillatory habits with a hard and fast interval.
- Toroidal (Quasiperiodic) Attractors: the system follows trajectories that wind round a donut-like construction within the part house. In contrast to restrict cycles, these trajectories by no means actually repeat however they continue to be certain to a particular area.
- Unusual (Chaotic) Attractors: characterised by aperiodic habits that by no means repeats precisely but stays bounded inside a finite area of part house. These attractors exhibit delicate dependence on preliminary circumstances, the place a tiny distinction will introduce important penalties over time — an indicator of chaos. Assume butterfly impact.
Setup
Within the following part, we are going to dive deeper into an instance of a quite simple NN structure able to stated habits, and exhibit some fairly examples. We’ll contact on Lyapunov exponents, and supply implementation for many who want to experiment with producing their very own Neural Community attractor artwork (and never within the generative AI sense).

We’ll use a grossly simplified one-layer NN with a suggestions loop. The structure consists of:
- Enter Layer:
- Array of dimension D (right here 16-32) inputs
- We’ll unconventionally label them as y₁, y₂, y₃, …, yD to spotlight that these are mapped from the outputs
- Acts as a shift register that shops earlier outputs
- Hidden Layer:
- Accommodates N neurons (right here fewer than D, ~4-8)
- We’ll label them x₁, x₂, …, xN
- tanh() activation is utilized for squashing
- Output Layer
- Single output neuron (y₀)
- Combines the hidden layer outputs with biases — sometimes, we use biases to offset outputs by including them; right here, we used them for scaling, so they’re factually an array of weights
- Connections:
- Enter to Hidden: Weight matrix w[i,j] (randomly initialized between -1 and 1)
- Hidden to Output: Bias weights b[i] (randomly initialized between 0 and s)
- Suggestions Loop:
- The output y₀ is fed again to the enter layer, making a dynamic map
- Acts as a shift register (y₁ = earlier y₀, y₂ = earlier y₁, and so on.)
- This suggestions is what creates the dynamical system habits
- Key Formulation:
- Hidden layer: u[i] = Σ(w[i,j] * y[j]); x[i] = tanh(u[i])
- Output: y₀ = Σ(b[i] * x[i])
The vital elements that make this community generate attractors:
- The suggestions loop turns a easy feedforward community right into a dynamical system
- The nonlinear activation operate (tanh) allows advanced behaviors
- The random weight initialization (managed by the random seed) creates completely different attractor patterns
- The scaling issue s impacts the dynamics of the system and may push it into chaotic regimes
In an effort to examine how inclined the system is to chaos, we are going to calculate the Lyapunov exponents for various units of parameters. Lyapunov exponent is a measure of the instability of a dynamical system…

…the place nt is various time steps, Δyokay is a distance between the states y(xi) and y(xi+ϵ) at a cut-off date; ΔZ(0) represents an preliminary infinitesimal (very small) separation between two close by beginning factors, and ΔZ(t) is the separation after time t. For steady programs converging to a hard and fast level or a steady attractor this parameter is lower than 0, for unstable (diverging, and, due to this fact, chaotic programs) it’s larger than 0.
Let’s code it up! We’ll solely use NumPy and default Python libraries for the implementation.
import numpy as np
from typing import Tuple, Record, Elective
class NeuralAttractor:
"""
N : int
Variety of neurons within the hidden layer
D : int
Dimension of the enter vector
s : float
Scaling issue for the output
"""
def __init__(self, N: int = 4, D: int = 16, s: float = 0.75, seed: Elective[int] =
None):
self.N = N
self.D = D
self.s = s
if seed just isn't None:
np.random.seed(seed)
# Initialize weights and biases
self.w = 2.0 * np.random.random((N, D)) - 1.0 # Uniform in [-1, 1]
self.b = s * np.random.random(N) # Uniform in [0, s]
# Initialize state vector constructions
self.x = np.zeros(N) # Neuron states
self.y = np.zeros(D) # Enter vector
We initialize the NeuralAttractor
class with some fundamental parameters — variety of neurons within the hidden layer, variety of components within the enter array, scaling issue for the output, and random seed. We proceed to initialize the weights and biases randomly, and x and y states. These weights and biases won’t be optimized — they may keep put, no gradient descent this time.
def reset(self, init_value: float = 0.001):
"""Reset the community state to preliminary circumstances."""
self.x = np.ones(self.N) * init_value
self.y = np.zeros(self.D)
def iterate(self) -> np.ndarray:
"""
Carry out one iteration of the community and return the neuron outputs.
"""
# Calculate the output y0
y0 = np.sum(self.b * self.x)
# Shift the enter vector
self.y[1:] = self.y[:-1]
self.y[0] = y0
# Calculate the neuron inputs and apply activation fn
for i in vary(self.N):
u = np.sum(self.w[i] * self.y)
self.x[i] = np.tanh(u)
return self.x.copy()
Subsequent, we are going to outline the iteration logic. We begin each iteration with the suggestions loop — we implement the shift register circuit by shifting all y components to the precise, and compute the newest y0 output to position it into the primary aspect of the enter.
def generate_trajectory(self, tmax: int, discard: int = 0) -> Tuple[np.ndarray,
np.ndarray]:
"""
Generate a trajectory of the states for tmax iterations.
-----------
tmax : int
Complete variety of iterations
discard : int
Variety of preliminary iterations to discard
"""
self.reset()
# Discard preliminary transient
for _ in vary(discard):
self.iterate()
x1_traj = np.zeros(tmax)
x2_traj = np.zeros(tmax)
for t in vary(tmax):
x = self.iterate()
x1_traj[t] = x[0]
x2_traj[t] = x[1]
return x1_traj, x2_traj
Now, we outline the operate that can iterate our community map over the tmax variety of time steps and output the states of the primary two hidden neurons for visualization. We will use any hidden neurons, and we may even visualize 3D state house, however we are going to restrict our creativeness to 2 dimensions.
That is the gist of the system. Now, we are going to simply outline some line and phase magic for fairly visualizations.
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.collections as mcoll
import matplotlib.path as mpath
from typing import Tuple, Elective, Callable
def make_segments(x: np.ndarray, y: np.ndarray) -> np.ndarray:
"""
Create checklist of line segments from x and y coordinates.
-----------
x : np.ndarray
X coordinates
y : np.ndarray
Y coordinates
"""
factors = np.array([x, y]).T.reshape(-1, 1, 2)
segments = np.concatenate([points[:-1], factors[1:]], axis=1)
return segments
def colorline(
x: np.ndarray,
y: np.ndarray,
z: Elective[np.ndarray] = None,
cmap = plt.get_cmap("jet"),
norm = plt.Normalize(0.0, 1.0),
linewidth: float = 1.0,
alpha: float = 0.05,
ax = None
):
"""
Plot a coloured line with coordinates x and y.
-----------
x : np.ndarray
X coordinates
y : np.ndarray
Y coordinates
"""
if ax is None:
ax = plt.gca()
if z is None:
z = np.linspace(0.0, 1.0, len(x))
segments = make_segments(x, y)
lc = mcoll.LineCollection(
segments, array=z, cmap=cmap, norm=norm, linewidth=linewidth, alpha=alpha
)
ax.add_collection(lc)
return lc
def plot_attractor_trajectory(
x: np.ndarray,
y: np.ndarray,
skip_value: int = 16,
color_function: Elective[Callable] = None,
cmap = plt.get_cmap("Spectral"),
linewidth: float = 0.1,
alpha: float = 0.1,
figsize: Tuple[float, float] = (10, 10),
interpolate_steps: int = 3,
output_path: Elective[str] = None,
dpi: int = 300,
present: bool = True
):
"""
Plot an attractor trajectory.
Parameters:
-----------
x : np.ndarray
X coordinates
y : np.ndarray
Y coordinates
skip_value : int
Variety of factors to skip for sparser plotting
"""
fig, ax = plt.subplots(figsize=figsize)
if interpolate_steps > 1:
path = mpath.Path(np.column_stack([x, y]))
verts = path.interpolated(steps=interpolate_steps).vertices
x, y = verts[:, 0], verts[:, 1]
x_plot = x[::skip_value]
y_plot = y[::skip_value]
if color_function is None:
z = abs(np.sin(1.6 * y_plot + 0.4 * x_plot))
else:
z = color_function(x_plot, y_plot)
colorline(x_plot, y_plot, z, cmap=cmap, linewidth=linewidth, alpha=alpha, ax=ax)
ax.set_xlim(x.min(), x.max())
ax.set_ylim(y.min(), y.max())
ax.set_axis_off()
ax.set_aspect('equal')
plt.tight_layout()
if output_path:
fig.savefig(output_path, dpi=dpi, bbox_inches='tight')
return fig
The capabilities written above will take the generated state house trajectories and visualize them. As a result of the state house could also be densely stuffed, we are going to skip each eighth, sixteenth or 32th time level to sparsify our vectors. We additionally don’t need to plot these in a single strong shade, due to this fact we’re coding the colour as a periodic operate (np.sin(1.6 * y_plot + 0.4 * x_plot)) primarily based on the x and y coordinates of the determine axis. The multipliers for the coordinates are arbitrary and occur to generate good easy shade maps, to your liking.
N = 4
D = 32
s = 0.22
seed=174658140
tmax = 100000
discard = 1000
nn = NeuralAttractor(N, D, s, seed=seed)
# Generate trajectory
x1, x2 = nn.generate_trajectory(tmax, discard)
plot_attractor_trajectory(
x1, x2,
output_path='trajectory.png',
)
After defining the NN and iteration parameters, we will generate the state house trajectories. If we spend sufficient time poking round with parameters, we are going to discover one thing cool (I promise!). If guide parameter grid search labor just isn’t precisely our factor, we may add a operate that checks what proportion of the state house is roofed over time. If after t = 100,000 iterations (besides the preliminary 1,000 “heat up” time steps) we solely touched a slim vary of values of the state house, we’re doubtless caught in some extent. As soon as we discovered an attractor that isn’t so shy to take up extra state house, we will plot it utilizing default plotting params:

One of many steady varieties of attractors is the restrict cycle attractor (parameters: N = 4, D = 32, s = 0.22, seed = 174658140). It seems to be like a single, closed loop trajectory in part house. The orbit follows a daily, periodic path over time sequence. I cannot embrace the code for Lyapunov exponent calculation right here to give attention to the visible facet of the generated attractors extra, however one can discover it beneath this hyperlink, if . The Lyapunov exponent for this attractor (λ=−3.65) is adverse, indicating stability: mathematically, this exponent will result in the state of the system decaying, or converging, to this basin of attraction over time.
If we hold rising the scaling issue, we usually tend to tune up the values within the circuit, and maybe extra prone to discover one thing attention-grabbing.

Right here is the toroidal (quasiperiodic) attractor (parameters: N = 4, D = 32, s = 0.55, seed = 3160697950). It nonetheless has an ordered construction of sheets that wrap round in organized, quasiperiodic patterns. The Lyapunov exponent for this attractor has the next worth, however continues to be adverse (λ=−0.20).
As we additional enhance the scaling issue s, the system turns into extra susceptible to chaos. The unusual (chaotic) attractor emerges with the next parameters: N = 4, D = 16, s = 1.4, seed = 174658140). It’s characterised by an erratic, unpredictable sample of trajectories that by no means repeat. The Lyapunov exponent for this attractor is optimistic (λ=0.32), indicating instability (divergence from an initially very shut state over time) and chaotic habits. That is the “butterfly impact” attractor.

As we additional enhance the scaling issue s, the system turns into extra susceptible to chaos. The unusual (chaotic) attractor emerges with the next parameters: N = 4, D = 16, s = 1.4, seed = 174658140. It’s characterised by an erratic, unpredictable sample of trajectories that by no means repeat. The Lyapunov exponent for this attractor is optimistic (λ=0.32), indicating instability (divergence from an initially very shut state over time) and chaotic habits. That is the “butterfly impact” attractor.
Simply one other affirmation that aesthetics could be very mathematical, and vice versa. Essentially the most visually compelling attractors usually exist on the fringe of chaos — give it some thought for a second! These constructions are advanced sufficient to exhibit intricate habits, but ordered sufficient to take care of coherence. This resonates with observations from numerous artwork varieties, the place steadiness between order and unpredictability usually creates probably the most partaking experiences.
An interactive widget to generate and visualize these attractors is accessible right here. The supply code is out there, too, and invitations additional exploration. The concepts behind this venture have been largely impressed by the work of J.C. Sprott [3].
References
[1] B. Poucet and E. Save, Attractors in Reminiscence (2005), Science DOI:10.1126/science.1112555.
[2] Y.J.F. Kpomahou et al., Chaotic Behaviors and Coexisting Attractors in a New Nonlinear Dissipative Parametric Chemical Oscillator (2022), Complexity DOI:10.1155/2022/9350516.
[3] J.C. Sprott, Synthetic Neural Web Attractors (1998), Computer systems & Graphics DOI:10.1016/S0097-8493(97)00089-7.