Skip to content

Instantly share code, notes, and snippets.

View giuseppebonaccorso's full-sized avatar
🎯
Focusing

Giuseppe Bonaccorso giuseppebonaccorso

🎯
Focusing
137 followers · 2 following
View GitHub Profile
@giuseppebonaccorso
giuseppebonaccorso / sanger.py
Last active February 13, 2024 19:34
Sanger's rule (Hebbian Learning)
import numpy as np
from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler
# Set random seed for reproducibility
np.random.seed(1000)
# Create and scale dataset
X, _ = make_blobs(n_samples=500, centers=2, cluster_std=5.0, random_state=1000)
@giuseppebonaccorso
giuseppebonaccorso / hmm_fixed_delay_smoothing.py
Created August 28, 2017 09:26
Fixed-delay smoothing in HMM
import numpy as np
from Queue import Queue
class HMM:
def __init__(self, transition_matrix, observation_matrix, delay, initial_state):
self.TM = transition_matrix
self.OM = observation_matrix
self.delay = delay
@giuseppebonaccorso
giuseppebonaccorso / knn_benchmark.py
Created August 29, 2017 14:56
K-Nearest Neighbors Perfomance Benchmark
from sklearn.datasets import make_blobs
from sklearn.neighbors import NearestNeighbors
import matplotlib.pyplot as plt
import multiprocessing
import numpy as np
import time
# Set random seed (for reproducibility)
np.random.seed(1000)
@giuseppebonaccorso
giuseppebonaccorso / fim.py
Created September 2, 2017 15:02
Fisher Information Matrix
import numpy as np
import tensorflow as tf
from sklearn.datasets import make_blobs
# Set random seed (for reproducibility)
np.random.seed(1000)
# Create dataset
nb_samples=2000
@giuseppebonaccorso
giuseppebonaccorso / model_free_collaborative_filtering.py
Last active April 17, 2018 22:14
A model-free collaborative recommendation system in 20 lines of Python
from scipy.sparse import dok_matrix
from sklearn.metrics.pairwise import pairwise_distances
import numpy as np
# Set random seed (for reproducibility)
np.random.seed(1000)
# Create a dummy user-item dataset
nb_users = 1000
@giuseppebonaccorso
giuseppebonaccorso / quickprop.py
Created September 15, 2017 11:43
Quickprop example
from sklearn.datasets import make_classification
import numpy as np
# Set random seed (for reproducibility)
np.random.seed(1000)
def sigmoid(arg):
return 1.0 / (1.0 + np.exp(-arg))
@giuseppebonaccorso
giuseppebonaccorso / hopfield.py
Created September 20, 2017 12:33
Hopfield Network
import matplotlib.pyplot as plt
import numpy as np
# Set random seed for reproducibility
np.random.seed(1000)
nb_patterns = 4
pattern_width = 4
pattern_height = 4
max_iterations = 10
@giuseppebonaccorso
giuseppebonaccorso / brain-state-in-a-box.py
Created September 22, 2017 09:27
Brain-State-in-a-Box Network
import matplotlib.pyplot as plt
import numpy as np
# Set random seed for reproducibility
np.random.seed(1000)
nb_patterns = 4
pattern_width = 4
pattern_height = 4
max_iterations = 100
@giuseppebonaccorso
giuseppebonaccorso / rubner-tavan-pca-network.py
Last active December 4, 2017 15:58
PCA with Rubner-Tavan Networks
from sklearn.datasets import load_digits
import numpy as np
# Set random seed for reproducibility
np.random.seed(1000)
# Load MNIST dataset
X, Y = load_digits(return_X_y=True)
X /= 255.0
@giuseppebonaccorso
giuseppebonaccorso / passive_aggressive_classification.py
Last active November 13, 2017 01:07
Passive Aggressive Classification
import numpy as np
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
# Set random seed (for reproducibility)
np.random.seed(1000)
nb_samples = 5000