Discrete Uniform Distribution By: Bindeshwar Singh Kushwaha PostNetwork Academy Discrete Uniform Distribution A random variable \( X \) is said to have a discrete uniform distribution if it takes integer values from \( a \) to \( b \) with equal probability. The number of possible values is \[ n = b – a + […]
Discrete Uniform Distribution in Statistics Read More »
Naive Bayes Classification Algorithm for Weather Dataset Author: Bindeshwar Singh Kushwaha | PostNetwork Academy Introduction to Naive Bayes Classifier Naive Bayes is a probabilistic classification algorithm. It is based on Bayes’ Theorem and the naive independence assumption. Suppose we have a feature vector \(\mathbf{X} = (x_1, x_2, …, x_n)\) and a class \(y\). Bayes Theorem:
Naive Bayes Classification Algorithm for Weather Dataset Read More »
Text Classification with Bag of Words and Naive Bayes Author: Bindeshwar Singh Kushwaha | PostNetwork Academy Understanding Text with Machine Learning Processing and understanding text allows extraction of meaningful information from raw data. Text data can be structured into features that machine learning algorithms can analyze. Machine learning approaches include supervised, unsupervised, and deep learning
Text Classification with Bag of Words and Naive Bayes Read More »
Fitting of Poisson Distribution Bindeshwar Singh Kushwaha — PostNetwork Academy Introduction Master the technique of fitting the Poisson distribution to real-world frequency data. This tutorial shows a step-by-step method to calculate theoretical frequencies for observed datasets. Key Concepts & Techniques Introduction to Fitting: Fit a theoretical Poisson distribution to experimental data to derive expected frequencies.
Fitting of Poisson Distribution Read More »
📌 What is a Filter / Kernel / Mask? A filter (also called a kernel or mask) is a small matrix of numbers used to transform an image. Purpose: Emphasize features like edges, textures, or smooth out noise. Filters are applied via convolution or correlation. In convolution, the filter “slides” over the image and computes
Filters or Kernels in Image Processing Read More »
Gradient of Softmax + Cross-Entropy w.r.t Logits Author: Bindeshwar Singh Kushwaha – PostNetwork Academy Goal We want to compute: $$ \frac{\partial L}{\partial z_j} $$ Notation: Logits: \(z = [z_1, z_2, \dots, z_C]\) Softmax: \(\hat{y}_i = \frac{e^{z_i}}{\sum_{k=1}^{C} e^{z_k}}\) Cross-Entropy Loss: \(L = -\sum_{i=1}^{C} y_i \log \hat{y}_i\), where \(y_i\) is one-hot. [Insert Neural Network Diagram Here] Loss
Gradient of Softmax + Cross-Entropy w.r.t Logits Read More »
Understanding Neural Networks: Softmax, Cross-Entropy, and Backpropagation Author: Bindeshwar Singh Kushwaha – PostNetwork Academy Neural Network with Softmax + Cross-Entropy Input Layer: The network receives 3 input features, denoted \(x_1, x_2, x_3\). Hidden Layer: 2 neurons in the hidden layer with activations \(a^{(1)}\) and \(a^{(2)}\). Output Layer: 2 outputs \(z^{(3)}, z^{(4)}\), passed through softmax. Softmax
Understanding Neural Networks: Softmax, Cross-Entropy, and Backpropagation Read More »
Iris Classification Neural Network with Backpropagation Bindeshwar Singh Kushwaha PostNetwork Academy Forward Propagation Step 1 Dataset features: \( x_1 = \text{Sepal length}, \; x_2 = \text{Sepal width}, \; x_3 = \text{Petal length}, \; x_4 = \text{Petal width} \) Forward Propagation Step 2 \( z_{h1} = w_{11}x_1 + w_{21}x_2 + w_{31}x_3 + w_{41}x_4
Iris Classification Neural Network with Backpropagation Read More »
Spectrogram of Speech Author: Bindeshwar Singh Kushwaha — PostNetwork Academy What is a Spectrogram? Spectrogram — a visual representation of sound. Shows how the frequency content of a signal changes over time. Axes of a spectrogram: X-axis: Time (seconds) Y-axis: Frequency (Hz) Color / Intensity: Amplitude or Power (dB) Computed using the Short-Time Fourier
Spectrogram of Speech in Python Read More »
Understanding Speech Data using Python Author: Bindeshwar Singh Kushwaha – Postnetwork Academy Introduction Speech is a continuous acoustic signal that we digitize so computers can analyze and learn from it. This post walks you through what speech data is, how to load and visualize it in Python using librosa, and why both time-domain and frequency-domain
Understanding Speech Data using Python Read More »