Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Data Science: Intro To Deep Learning With Python In 2025
Rating: 4.1 out of 5(67 ratings)
10,119 students

Data Science: Intro To Deep Learning With Python In 2025

Learn to create Deep Learning Algorithms in Python
Created byPianalytix • 75,000+ Students Worldwide
Last updated 9/2025
English
English [Auto],

What you'll learn

  • Understand the intuition behind Artificial Neural Networks
  • Build artificial neural networks with Tensorflow
  • Classify images, data using deep learning
  • Apply Convolutional Neural Networks in practice

Course content

1 section • 11 lectures • 1h 54m total length

  • Intro to deep learning4:40

    Explore how deep learning uses neural networks to learn patterns from data, enabling applications from facial recognition and voice assistants to medical imaging and self-driving cars.

  • All you need to know about dataset5:02
  • Binary classification4:37

    Explore binary classification with tumor size as the feature and a sigmoid-based hypothesis to predict malignant versus benign tumors, and note softmax, optimization, and minimizing error for nonlinear boundaries.

  • Forward Propagation15:50

    Explore forward propagation in a deep neural network, computing z and activations with weights, biases, and vector operations. See how sigmoid activation enables binary classification and gradient descent updates.

  • Activation Functions8:44

    Explore activation functions and why non-linearity enables neural networks to learn patterns. See how ReLU, step functions, and sigmoid activations create non-linear decision boundaries compared to linear hypotheses.

  • BackPropagation18:28

    Explore how backpropagation computes layer-wise gradients from the output to the input, using the chain rule and derivatives of activation functions, to drive gradient descent updates of weights and biases.

  • Gradient descent6:54

    Explore gradient descent for updating weights and biases, and analyze learning rate alpha 0.01 effects, convergence versus overshoot, random initialization, and how backpropagation guides updates to avoid local minima.

  • Building blocks Of DNN7:11

    Explore the building blocks of a neural network, layers and neurons, through forward and backward propagation, gradients, cost, and parameter updates for training from scratch.

  • DNN from scratch22:51

    Explore building a deep neural network from scratch in Python using numpy, h5py, and matplotlib, learning forward and backward propagation, cost, and training on two-class cats dataset in Google Colaboratory.

  • MNIST Fashion in TF framework19:54

    Learn to train a fashion MNIST classifier with TensorFlow 2 and the Keras sequential API, building a flatten layer and dense layers, normalizing data, and evaluating on a 60k/10k split.

  • Download the code files0:29

Requirements

  • Some prior coding experience with python is required.

Description

Neural networks are a family of machine learning algorithms that are generating a lot of excitement. They are a technique that is inspired by how the neurons in our brains function. They are based on a simple idea: given certain parameters, it is possible to combine them in order to predict a certain result. For example, if you know the number of pixels in an image, there are ways of knowing which number is written in the image. The data that enters passes through various “ layers” in which a series of adjusted learning rules are applied by a weighted function. After passing through the last layer, the results are compared with the “correct” results, and the parameters are adjusted.

Although the algorithms and the learning process in general are complex, one the network has learned, it can freeze the various weights and function in a memory or execution mode. Google uses these types of algorithms, for example, for image searches.

There is no single definition for the meaning of Deep Learning. In general, when we talk of Deep Learning, we are referring to a group of Machine Learning algorithms based on neural networks that, as we have seen, are characterized by cascade data processing. The entrance signal passes through the various stages, and in each one, they are subjected to a non-linear transformation. This helps to extract and transform the variable according to the determined parameters (weights or boundaries). There isn’t an established limit for the number of stages that a neural network must contain to be considered Deep Learning. However, it is thought that Deep Learning arose in the 80’s, using a model which had 5 or 6 layers. It was (and is) called the neocognitron and was created by the Japanese researcher Kunihiki Fukushima. Neural networks are very effective in identifying patterns.

An example worth highlighting of the application of Deep Learning is the project carried out by Google and the Universities of Stanford and Massachusetts. It aimed to improve the natural language processing techniques of a type of AI called Recurrent Neural Network Language Model (RNNLM). It’s used for automatic translations and creating subtitles, among other thing. Basically, it builds up phrases word by words, basing each word on the previous one and in this way, it can even write poems.

Module 1

1. Introduction to Deep Learning and TensorFlow

2. Basics of Neural Networks

3. Designing a shallow neural network (Scratch and python) (Project)

4. Deeper neural network using TensorFlow. (Project)

Who this course is for:

  • Beginners In Python
  • Beginners In Deep Learning
  • Beginners In Machine Learning

Report abuse