Deep Learning with PyTorch for Medical Image Analysis

Course content

  • Introduction
  • Crash Course: NumPy
  • Machine Learning Concepts Overview
  • PyTorch Basics
  • CNN – Convolutional Neural Networks
  • Medical Imaging – A short Introduction
  • Data Formats in Medical Imaging
  • Pneumonia-Classification
  • Cardiac-Detection
  • Atrium-Segmentation
  • Capstone-Project: Lung Tumor Segmentation
  • 3D Liver and Liver Tumor Segmentation

The Complete Self-Driving Car Course – Applied Deep Learning

Course content

  • Introduction
  • Installation
  • Python Crash Course (Optional)
  • NumPy Crash Course (Optional)
  • Computer Vision: Finding Lane Lines
  • The Perceptron
  • Keras
  • Deep Neural Networks
  • Multiclass Classification
  • MN 1ST Image Recognition
  • Convolutional Neural Networks
  • Classifying Road Symbols
  • Polynomial Regression
  • Behavioural Cloning

Deep Learning: Convolutional Neural Networks in Python

Course content

  • Welcome
  • Google Colab
  • Machine Learning and Neurons
  • Feedforward Artificial Neural Networks
  • Convolutional Neural Networks
  • Natural Language Processing (NLP)
  • Convolution In-Depth
  • Convolutional Neural Network Description
  • Practical Tips
  • In-Depth: Loss Functions
  • In-Depth: Gradient Descent
  • Setting Up Your Environment (FAQ by Student Request)
  • Extra Help With Python Coding for Beginners (FAQ by Student Request)
  • Effective Learning Strategies for Machine Learning (FAQ by Student Request)
  • Appendix / FAQ Finale

Deep Learning A-Z 2023: Neural Networks, AI & ChatGPT Prize

Course content

  • Welcome to the course!
  • Part 1 – Artificial Neural Networks
  • ANN Intuition
  • Building an ANN
  • Part 2 – Convolutional Neural Networks
  • CNN Intuition
  • Building a CNN
  • Part 3 – Recurrent Neural Networks
  • RNN Intuition
  • Building a RNN
  • Evaluating and Improving the RNN
  • Part 4 – Self Organizing Maps
  • SOMs Intuition
  • Building a SOM
  • Mega Case Study
  • Part 5 – Boltzmann Machines
  • Boltzmann Machine Intuition
  • Building a Boltzmann Machine
  • Part 6 – AutoEncoders
  • AutoEncoders Intuition
  • Building an AutoEncoder
  • Annex – Get the Machine Learning Basics
  • Regression & Classification Intuition
  • Data Preprocessing
  • Data Preprocessing in Python
  • Logistic Regression
  • Congratulations!! Don’t forget your Prize

Deep Learning Neural Networks with Chainer Training Course


14 hours (usually 2 days including breaks)


  • An understanding of artificial neural networks
  • Familiarity with deep learning frameworks (Caffe, Torch, etc.)
  • Python programming experience


  • AI Researchers
  • Developers


Chainer is an open source framework based on Python, built for accelerating research and implementing neural network models. It provides flexible, efficient, and simplified approaches to developing deep learning algorithms.

This instructor-led, live training (online or onsite) is aimed at researchers and developers who wish to use Chainer to build and train neural networks in Python while making the code easy to debug.

By the end of this training, participants will be able to:

  • Set up the necessary development environment to start developing neural network models.
  • Define and implement neural network models using a comprehensible source code.
  • Execute examples and modify existing algorithms to optimize deep learning training models while leveraging GPUs for high performance.

Format of the Course

  • Interactive lecture and discussion.
  • Lots of exercises and practice.
  • Hands-on implementation in a live-lab environment.

Course Customization Options

  • To request a customized training for this course, please contact us to arrange.

Course Outline


  • Chainer vs Caffe vs Torch
  • Overview of Chainer features and components

Getting Started

  • Understanding the trainer structure
  • Installing Chainer, CuPy, and NumPy
  • Defining functions on variables

Training Neural Networks in Chainer

  • Constructing a computational graph
  • Running MNIST dataset examples
  • Updating parameters using an optimizer
  • Processing images to evaluate results

Working with GPUs in Chainer

  • Implementing recurrent neural networks
  • Using multiple GPUs for parallelization

Implementing Other Neural Network Models

  • Defining RNN models and running examples
  • Generating images with Deep Convolutional GAN
  • Running Reinforcement Learning examples


Summary and Conclusion

The 7 Must-Know Deep Learning Algorithms

The field of artificial intelligence (AI) has grown rapidly in recent times, leading to the development of deep learning algorithms. With the launch of AI tools such as DALL-E and OpenAI, deep learning has emerged as a key area of research. However, with an abundance of available algorithms, it can be difficult to know which ones are the most crucial to understand.

Dive into the fascinating world of deep learning and explore the top, must-know algorithms crucial to understanding artificial intelligence.

1. Convolutional Neural Networks (CNNs)

Convolutional Neural Networks (CNNs), also known as ConvNets, are neural networks that excel at object detection, image recognition, and segmentation. They use multiple layers to extract features from the available data. CNNs mainly consist of four layers:

  1. Convolution layer
  2. Rectified Linear Unit (ReLU)
  3. Pooling Layer
  4. Fully Connected Layer

These four layers provide a working mechanism for the network. The convolution layer is the first layer in CNNs, which filters out complex features from the data. Then, the ReLU maps data to train the network. After that, the process sends the map to the pooling layer, which reduces sampling, and converts the data from 2D to a linear array. Finally, the fully connected layer forms a flattened linear matrix used as input to detect images or other data types.

2. Deep Belief Networks

Deep Belief Networks (DBNs) are another popular architecture for deep learning that allows the network to learn patterns in data with artificial intelligence features. They are ideal for tasks such as face recognition software and image feature detection.

The DBN mechanism involves different layers of Restricted Boltzmann Machines (RBM), which is an artificial neural network that helps in learning and recognizing patterns. The layers of DBN follow the top-down approach, allowing communication throughout the system, and the RBM layers provide a robust structure that can classify data based on different categories.

3. Recurrent Neural Networks (RNNs)

Recurrent Neural Network (RNN) is a popular deep learning algorithm with a wide range of applications. The network is best known for its ability to process sequential data and design language models. It can learn patterns and predict outcomes without mentioning them in the code. For example, the Google search engine uses RNN to auto-complete searches by predicting relevant searches.

The network works with interconnected node layers that help memorize and process input sequences. It can then work through those sequences to automatically predict possible outcomes. Additionally, RNNs can learn from prior inputs, allowing them to evolve with more exposure. Therefore, RNNs are ideal for language modeling and sequential modeling.

4. Long Short Term Memory Networks (LSTMs)

Long Short Term Memory Networks (LSTMs) are a Recurrent Neural Network (RNN) type that differs from others in their ability to work with long-term data. They have exceptional memory and predictive capabilities, making LSTMs ideal for applications like time series predictions, natural language processing (NLP), speech recognition, and music composition.

LSTM networks consist of memory blocks arranged in a chain-like structure. These blocks store relevant information and data that may inform the network in the future while removing any unnecessary data to remain efficient.

During data processing, the LSTM changes cell states. First, it removes irrelevant data through the sigmoid layer. Then it processes new data, evaluates necessary parts, and replaces the previous irrelevant data with the new data. Finally, it determines the output based on the current cell state that has filtered data.

The ability to handle long-term data sets LSTMs apart from other RNNs, making them ideal for applications that require such capabilities.

5. Generative Adversarial Networks

Generative Adversarial Networks (GANs) are a type of deep learning algorithm that supports generative AI. They are capable of unsupervised learning and can generate results on their own by training through specific datasets to create new data instances.

The GAN model consists of two key elements: a generator and a discriminator. The generator is trained to create fake data based on its learning. In contrast, the discriminator is trained to check the output for any fake data or errors and rectify the model based on it.

GANs are widely used for image generation, such as enhancing the graphics quality in video games. They are also useful for enhancing astronomical images, simulating gravitational lenses, and generating videos. GANs remain a popular research topic in the AI community, as their potential applications are vast and varied.

6. Multilayer Perceptrons

Multilayer Perceptron (MLP) is another deep learning algorithm, which is also a neural network with interconnected nodes in multiple layers. MLP maintains a single data flow dimension from input to output, which is known as feedforward. It is commonly used for object classification and regression tasks.

The structure of MLP involves multiple input and output layers, along with several hidden layers, to perform filtering tasks. Each layer contains multiple neurons that are interconnected with each other, even across layers. The data is initially fed to the input layer, from where it progresses through the network.

The hidden layers play a significant role by activating functions like ReLUs, sigmoid, and tanh. Subsequently, it processes the data and generates an output on the output layer.

This simple yet effective model is useful for speech and video recognition and translation software. MLPs have gained popularity due to their straightforward design and ease of implementation in various domains.

7. Autoencoders

Autoencoders are a type of deep learning algorithm used for unsupervised learning. It’s a feedforward model with a one-directional data flow, similar to MLP. Autoencoders are fed with input and modify it to create an output, which can be useful for language translation and image processing.

The model consists of three components: the encoder, the code, and the decoder. They encode the input, resize it into smaller units, then decode it to generate a modified version. This algorithm can be applied in various fields, such as computer vision, natural language processing, and recommendation systems.

Choosing the Right Deep Learning Algorithm

To select the appropriate deep learning approach, it is crucial to consider the nature of the data, the problem at hand, and the desired outcome. By understanding each algorithm’s fundamental principles and capabilities, you can make informed decisions.

Choosing the right algorithm can make all the difference in the success of a project. It is an essential step toward building effective deep learning models.


Explore the fascinating world of Capsule Networks with AI Terminologies 101, as we delve into their groundbreaking architecture, principles, and potential applications in computer vision and AI tasks.

Capsule Networks are a novel neural network architecture introduced by Geoffrey Hinton, one of the founding fathers of deep learning, as a means to address some of the limitations of traditional Convolutional Neural Networks (CNNs). In particular, Capsule Networks aim to better preserve spatial relationships between features in images or other input data. In this article, we will explore the concept of Capsule Networks, their underlying principles, and potential applications in AI and computer vision.

Traditional CNNs have been highly successful in various computer vision tasks, such as image classification and object detection. However, CNNs have certain limitations when it comes to capturing spatial hierarchies and relationships between parts of an object, as well as handling rotations and other transformations of the input data.

Capsule Networks were introduced to address these issues by incorporating the concept of “capsules” – small groups of neurons that encode the presence and properties of specific features, along with their spatial relationships. The key components of a Capsule Network are:

Capsules: Capsules are groups of neurons that work together to detect specific features within the input data. Each capsule is responsible for encoding the presence, pose, and other properties of a particular feature.

Dynamic Routing: Dynamic Routing is the process through which information is passed between capsules in different layers of the network. This mechanism allows the network to establish hierarchical relationships between features and adaptively route information based on the input data.

Reconstruction: Capsule Networks often include a reconstruction component, which attempts to recreate the original input from the network’s output. This component helps to ensure that the network has learned meaningful representations of the input data.

Capsule Networks have the potential to significantly improve the performance of various AI and computer vision tasks, as they inherently capture spatial relationships and can better handle different transformations of input data. Some possible applications of Capsule Networks include:

Image Classification: Capsule Networks can improve the accuracy of image classification tasks by better understanding the spatial relationships between features in images.

Object Detection: By preserving the spatial relationships between parts of an object, Capsule Networks can potentially enhance the performance of object detection algorithms.

Scene Understanding: Capsule Networks can contribute to a better understanding of complex scenes by capturing the relationships between different objects and their parts.

Capsule Networks represent an exciting development in AI and computer vision, offering a fresh approach to neural network architecture that can overcome some limitations of traditional CNNs. As research and development in this area continue, Capsule Networks may play a significant role in shaping the future of AI applications.

In future articles, we’ll dive deeper into other AI terminologies, like Graph Neural Networks, Federated Learning, and Feature Engineering. We’ll explain what they are, how they work, and why they’re important. By the end of this series, you’ll have a solid understanding of the key concepts and ideas behind AI, and you’ll be well-equipped to explore this exciting field further.

How Data Mining is Redefining AI and Machine Learning

Exploring the Synergy between Data Mining and AI in Advancing Machine Learning Technologies

Data mining, the process of discovering patterns and extracting valuable information from large datasets, has been a crucial component in the advancement of artificial intelligence (AI) and machine learning technologies. With the exponential growth of data generated by various industries, businesses, and individuals, the importance of data mining has become even more pronounced. The synergy between data mining and AI has led to the development of innovative machine learning algorithms and models that can analyze and interpret complex data, enabling machines to learn from experience and make intelligent decisions.

The evolution of AI and machine learning technologies has been driven by the increasing availability of data and the development of sophisticated data mining techniques. Data mining has enabled researchers and engineers to extract useful information from massive datasets, which can be used to train machine learning models. These models can then be used to make predictions, identify patterns, and solve complex problems across various domains, such as healthcare, finance, and manufacturing.

One of the key aspects of data mining that has contributed to the growth of AI and machine learning is feature extraction. Feature extraction involves identifying and selecting the most relevant variables or attributes from a dataset, which can be used to build predictive models. By selecting the most important features, data mining techniques can help reduce the complexity of machine learning models, making them more efficient and accurate.

Another significant contribution of data mining to AI and machine learning is the development of advanced algorithms for data preprocessing and transformation. Data preprocessing is an essential step in the machine learning process, as it helps clean and prepare the data for analysis. Data mining techniques, such as data cleaning, normalization, and transformation, can help improve the quality of the data and enhance the performance of machine learning models.

Moreover, data mining has played a crucial role in the development of unsupervised learning techniques, which are a subset of machine learning algorithms that do not require labeled data for training. Unsupervised learning techniques, such as clustering and dimensionality reduction, can help discover hidden patterns and structures in the data, which can be used to build more robust and accurate machine learning models.

The synergy between data mining and AI has also led to the emergence of new machine learning paradigms, such as deep learning and reinforcement learning. Deep learning, a subset of machine learning that involves training artificial neural networks to recognize patterns and make decisions, has been greatly influenced by data mining techniques. Data mining has enabled the development of advanced deep learning algorithms, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), which can process and analyze large volumes of data with high accuracy.

Reinforcement learning, another important area of AI and machine learning, has also benefited from data mining techniques. Reinforcement learning involves training machines to make decisions based on the outcomes of their actions, with the goal of maximizing a reward signal. Data mining has helped in the development of efficient reinforcement learning algorithms, such as Q-learning and deep Q-networks (DQNs), which can learn from large amounts of data and adapt to changing environments.

In conclusion, the synergy between data mining and AI has been instrumental in redefining the landscape of machine learning technologies. The advancements in data mining techniques have enabled the development of innovative machine learning algorithms and models that can process and analyze large volumes of data with high accuracy. As the amount of data generated by various industries continues to grow, the importance of data mining in the advancement of AI and machine learning technologies will only increase. The future of AI and machine learning will be shaped by the continuous evolution of data mining techniques and their integration with cutting-edge technologies, leading to more intelligent and efficient machines that can solve complex problems and make better decisions.