Auto-Encoder & Backpropagation by hand ✍️ lecture video ~ 📺 https://byhand.ai/cv/10

It took me a few years to invent this method to show both forward and backward passes for a non-trivial case of a multi-layer perceptron over a batch of inputs, plus gradient descents over multiple epochs, while being able to hand calculate each step and code in Excel at the same time.

= Chapters =
• Encoder & Decoder (00:00)
• Equation (10:09)
• 4-2-4 AutoEncoder (16:38)
• 6-4-2-4-6 AutoEncoder (18:39)
• L2 Loss (20:49)
• L2 Loss Gradient (27:31)
• Backpropagation (30:12)
• Implement Backpropagation (39:00)
• Gradient Descent (44:30)
• Summary (51:39)

#AIEngineering #MachineLearning #DeepLearning #LLMs #RAG #MLOps #Python #GitHubProjects #AIForBeginners #ArtificialIntelligence #NeuralNetworks #OpenSourceAI #DataScienceCareers

✉️ Our Telegram channels: https://t.me/addlist/0f6vfFbEMdAwODBk

GPU by hand ✍️ I drew this to show how a GPU speeds up an array operation of 8 elements in parallel over 4 threads in 2 clock cycles. Read more 👇

CPU
• It has one core.
• Its global memory has 120 locations (0-119).
• To use the GPU, it needs to copy data from the global memory to the GPU.
• After GPU is done, it will copy the results back.

GPU
• It has four cores to run four threads (0-3).
• It has a register file of 28 locations (0-27)
• This register file has four banks (0-3).
• All threads share the same register file.
• But they must read/write using the four banks.
• Each bank allows 2 reads (Read 0, Read 1) and 1 write in a single clock cycle.

#AIEngineering #MachineLearning #DeepLearning #LLMs #RAG #MLOps #Python #GitHubProjects #AIForBeginners #ArtificialIntelligence #NeuralNetworks #OpenSourceAI #DataScienceCareers

✉️ Our Telegram channels: https://t.me/addlist/0f6vfFbEMdAwODBk

What is torch.nn really?

When I started working with PyTorch, my biggest question was: "What is torch.nn?".

This article explains it quite well.

📌 Read

#pytorch #AIEngineering #MachineLearning #DeepLearning #LLMs #RAG #MLOps #Python #GitHubProjects #AIForBeginners #ArtificialIntelligence #NeuralNetworks #OpenSourceAI #DataScienceCareers

✉️ Our Telegram channels: https://t.me/addlist/0f6vfFbEMdAwODBk

😉 A list of the best YouTube videos
✅ To learn data science


1️⃣ SQL language


⬅️ Learning

💰 4-hour SQL course from zero to one hundred

💰 Window functions tutorial

⬅️ Projects

📎 Starting your first SQL project

💰 Data cleansing project

💰 Restaurant order analysis

⬅️ Interview

💰 How to crack the SQL interview?

➖➖➖

2️⃣ Python


⬅️ Learning

💰 12-hour Python for Data Science course

⬅️ Projects

💰 Python project for beginners

💰 Analyzing Corona Data with Python

⬅️ Interview

💰 Python interview golden tricks

💰 Python Interview Questions

➖➖➖

3️⃣ Statistics and machine learning


⬅️ Learning

💰 7-hour course in applied statistics

💰 Machine Learning Training Playlist

⬅️ Projects

💰 Practical ML Project

⬅️ Interview

💰 ML Interview Questions and Answers

💰 How to pass a statistics interview?

➖➖➖

4️⃣ Product and business case studies


⬅️ Learning

💰 Building strong product understanding

💰 Product Metric Definition

⬅️ Interview

💰 Case Study Analysis Framework

💰 How to shine in a business interview?

#DataScience #SQL #Python #MachineLearning #Statistics #BusinessAnalytics #ProductCaseStudies #DataScienceProjects #InterviewPrep #LearnDataScience #YouTubeLearning #CodingInterview #MLInterview #SQLProjects #PythonForDataScience

✉️ Our Telegram channels: https://t.me/addlist/0f6vfFbEMdAwODBk

Let's start at the top...

NumPy contains a broad array of functionality for fast numerical & mathematical operations in Python

The core data-structure within #NumPy is an ndArray (or n-dimensional array)

Behind the scenes - much of the NumPy functionality is written in the programming language C

NumPy functionality is used in other popular #Python packages including #Pandas, #Matplotlib, & #scikitlearn!

✉️ Our Telegram channels: https://t.me/addlist/0f6vfFbEMdAwODBk

Topic: Handling Datasets of All Types – Part 1 of 5: Introduction and Basic Concepts

---

1. What is a Dataset?

• A dataset is a structured collection of data, usually organized in rows and columns, used for analysis or training machine learning models.

---

2. Types of Datasets

• Structured Data: Tables, spreadsheets with rows and columns (e.g., CSV, Excel).

• Unstructured Data: Images, text, audio, video.

• Semi-structured Data: JSON, XML files containing hierarchical data.

---

3. Common Dataset Formats

• CSV (Comma-Separated Values)

• Excel (.xls, .xlsx)

• JSON (JavaScript Object Notation)

• XML (eXtensible Markup Language)

• Images (JPEG, PNG, TIFF)

• Audio (WAV, MP3)

---

4. Loading Datasets in Python

• Use libraries like pandas for structured data:

import pandas as pd
df = pd.read_csv('data.csv')

• Use libraries like json for JSON files:

import json
with open('data.json') as f:
    data = json.load(f)

---

5. Basic Dataset Exploration

• Check shape and size:

print(df.shape)

• Preview data:

print(df.head())

• Check for missing values:

print(df.isnull().sum())

---

6. Summary

• Understanding dataset types is crucial before processing.

• Loading and exploring datasets helps identify cleaning and preprocessing needs.

---

Exercise

• Load a CSV and JSON dataset in Python, print their shapes, and identify missing values.

---

#DataScience #Datasets #DataLoading #Python #DataExploration

The rest of the parts 👇
https://t.me/DataScienceM 🌟

Topic: Python Script to Convert a Shared ChatGPT Link to PDF – Step-by-Step Guide

---

### Objective

In this lesson, we’ll build a Python script that:

• Takes a ChatGPT share link (e.g., https://chat.openai.com/share/abc123)
• Downloads the HTML content of the chat
• Converts it to a PDF file using pdfkit and wkhtmltopdf

This is useful for archiving, sharing, or printing ChatGPT conversations in a clean format.

---

### 1. Prerequisites

Before starting, you need the following libraries and tools:

#### • Install pdfkit and requests

pip install pdfkit requests

#### • Install wkhtmltopdf

Download from:
https://wkhtmltopdf.org/downloads.html

Make sure to add the path of the installed binary to your system PATH.

---

### 2. Python Script: Convert Shared ChatGPT URL to PDF

import pdfkit
import requests
import os

# Define output filename
output_file = "chatgpt_conversation.pdf"

# ChatGPT shared URL (user input)
chat_url = input("Enter the ChatGPT share URL: ").strip()

# Verify the URL format
if not chat_url.startswith("https://chat.openai.com/share/"):
    print("Invalid URL. Must start with https://chat.openai.com/share/")
    exit()

try:
    # Download HTML content
    response = requests.get(chat_url)
    if response.status_code != 200:
        raise Exception(f"Failed to load the chat: {response.status_code}")

    html_content = response.text

    # Save HTML to temporary file
    with open("temp_chat.html", "w", encoding="utf-8") as f:
        f.write(html_content)

    # Convert HTML to PDF
    pdfkit.from_file("temp_chat.html", output_file)

    print(f"\n✅ PDF saved as: {output_file}")

    # Optional: remove temp file
    os.remove("temp_chat.html")

except Exception as e:
    print(f"❌ Error: {e}")

---

### 3. Notes

• This approach works only if the shared page is publicly accessible (which ChatGPT share links are).
• The PDF output will contain the web page version, including theme and layout.
• You can customize the PDF output using pdfkit options (like page size, margins, etc.).

---

### 4. Optional Enhancements

• Add GUI with Tkinter
• Accept multiple URLs
• Add PDF metadata (title, author, etc.)
• Add support for offline rendering using BeautifulSoup to clean content

---

### Exercise

• Try converting multiple ChatGPT share links to PDF
• Customize the styling with your own CSS
• Add a timestamp or watermark to the PDF

---

#Python #ChatGPT #PDF #WebScraping #Automation #pdfkit #tkinter

https://t.me/CodeProgrammer ✅