CoderzColumn : Artificial Intelligence Tutorials (Page: 2)

Artificial Intelligence Tutorials


Artificial intelligence (AI) is the emulation of human intelligence in devices that have been designed to behave and think like humans. The phrase can also be used to refer to any computer that demonstrates characteristics of the human intellect, like learning and problem-solving. Through CoderzColumn Ai tutorials, you will learn to code for these concepts:

  • Python Deep Learning Libraries
  • Image Classification
  • Object Detection
  • Text Classification
  • Text Generation
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs)
  • Interpret Predictions Of Deep Neural Network Models
  • Learning Rate Schedulers
  • Hyperparameters Tuning
  • Transfer Learning
  • Word Embeddings (GloVe Embeddings, FastText, etc)
  • RNNs (LSTMs) for Time Series
  • Text Classification using RNNs, LSTM & CNNs

For an in-depth understanding of the above concepts, check out the sections below.

Recent Artificial Intelligence Tutorials


Tags mxnet, text-generation, lstm, character-embeddings
Guide to Text Generation using MXNet RNNs (LSTM) (Character Embeddings)
Artificial Intelligence

Guide to Text Generation using MXNet RNNs (LSTM) (Character Embeddings)

The tutorial provides a guide on creating RNNs consisting of LSTM layers for solving text generation tasks. It uses a character-based approach to generate new text. The text data is encoded using the character embeddings approach.

Sunny Solanki  Sunny Solanki
Tags mxnet, text-generation, character-based, lstm
MXNet: Text Generation using LSTM Networks (Character-based RNNs)
Artificial Intelligence

MXNet: Text Generation using LSTM Networks (Character-based RNNs)

The tutorial covers how we can create Recurrent Neural Networks (RNNs) consisting of LSTM Layers for text generation tasks. It uses a character-based approach (works on characters instead of words/n-grams) to generate new text. The text is encoded using the bag of words approach before giving it to LSTM layers for processing.

Sunny Solanki  Sunny Solanki
Tags PyTorch, lstm, time-series, regression
PyTorch: LSTM Networks for Time-Series Data (Regression Tasks)
Artificial Intelligence

PyTorch: LSTM Networks for Time-Series Data (Regression Tasks)

The tutorial explains how to create Recurrent Neural Networks (RNNs) consisting of LSTM Layers to solve time-series regression tasks. LSTM networks are quite good at tasks involving time-series data.

Sunny Solanki  Sunny Solanki
Tags keras, LSTM, text-generation, embeddings
Keras: RNNs (LSTM) for Text Generation (Character Embeddings)
Artificial Intelligence

Keras: RNNs (LSTM) for Text Generation (Character Embeddings)

The tutorial explains how to design RNNs (LSTM Networks) for Text Generation Tasks using Python deep learning library Keras. The character embeddings approach is used to encode text data. It uses a character-based approach for text generation.

Sunny Solanki  Sunny Solanki
Tags keras, LSTM, text-generation
Keras: Text Generation using LSTM Networks (Character-based RNN)
Artificial Intelligence

Keras: Text Generation using LSTM Networks (Character-based RNN)

The tutorial explains how to create RNNs (LSTM Networks) using Python deep learning library Keras for Text Generation tasks. It uses a character-based approach for text generation.

Sunny Solanki  Sunny Solanki
Tags Pytorch, LSTM, text-generation, embeddings
Text Generation using PyTorch LSTM Networks (Character Embeddings)
Artificial Intelligence

Text Generation using PyTorch LSTM Networks (Character Embeddings)

The tutorial explains how to create LSTM Networks (Type of RNN) for Text Generation tasks in Python using Pytorch. The text data is encoded using the character embeddings approach. It uses a character-based approach for text generation.

Sunny Solanki  Sunny Solanki
Tags Pytorch, LSTM, text-generation
PyTorch: Text Generation using LSTM Networks (Character-based RNN)
Artificial Intelligence

PyTorch: Text Generation using LSTM Networks (Character-based RNN)

The tutorial explains how to create Recurrent Neural Networks (RNNs) consisting of LSTM layers for Text Generation tasks in Python using Pytorch. It uses a character-based approach for text generation.

Sunny Solanki  Sunny Solanki
Tags captum, pytorch, interpretation, text-classificat…
Captum: Interpret Predictions Of PyTorch Text Classification Network
Artificial Intelligence

Captum: Interpret Predictions Of PyTorch Text Classification Network

The tutorial explains how we can use Captum to explain/interpret predictions made by PyTorch networks for Text Classification tasks. Captum and PyTorch are both Python libraries.

Sunny Solanki  Sunny Solanki
Tags captum, pytorch, interpretation, image-classifica…
Captum: Interpret Predictions Of PyTorch Image Classification Networks
Artificial Intelligence

Captum: Interpret Predictions Of PyTorch Image Classification Networks

The tutorial explains how we can use Captum to explain predictions made by PyTorch (Python Deep Learning Library) Image classification networks. It explains various algorithms available from the library.

Sunny Solanki  Sunny Solanki
Tags captum, interpretation, pytorch-networks
Captum: Interpret Predictions Of PyTorch Networks
Artificial Intelligence

Captum: Interpret Predictions Of PyTorch Networks

The captum is a Python library designed specifically to interpret the predictions made by PyTorch networks. PyTorch is a Python deep learning library. The tutorial explains the usage of various algorithms available from Captum.

Sunny Solanki  Sunny Solanki
Python Deep Learning Libraries

Python Deep Learning Libraries


Deep learning is a field in Machine Learning that uses deep neural networks to solve tasks. The neural networks with generally more than one hidden layer are referred to as deep neural networks.

Many real-world tasks like object detection, image classification, image segmentation, etc can not be solved with simple machine learning models (decision trees, random forest, logistic regression, etc). Research has shown that neural networks with many layers are quite good at solving these kinds of tasks involving unstructured data (Image, text, audio, video, etc). Deep neural networks nowadays can have different kinds of layers like convolution, recurrent, etc apart from dense layers.

Python has many famous deep learning libraries (PyTorch, Keras, JAX, Flax, MXNet, Tensorflow, Sonnet, Haiku, PyTorch Lightning, Scikeras, Skorch, etc) that let us create deep neural networks to solve complicated tasks.

Image Classification

Image Classification


Image classification is a sub-field under computer vision and image processing that identifies an object present in an image and assigns a label to an image based on it. Image classification generally works on an image with a single object present in it.

Over the years, many deep neural networks (VGG, ResNet, AlexNet, MobileNet, etc) were developed that solved image classification task with quite a high accuracy. Due to the high accuracy of these algorithms, many Python deep learning libraries started providing these neural networks. We can simply load these networks with weights and make predictions using them.

Python libraries PyTorch and MXNet have helper modules named 'torchvision' and 'gluoncv’ respectively that provide an implementation of image classification networks.

Object Detection

Object Detection


Object detection is a sub-field of computer vision and image processing that detect presence of one or more objects in an image and draws a bounding box around them with labels above. It detects semantic objects present in an image.

Object detection has many applications like image captioning, image annotation, vehicle counting, activity recognition, face detection, etc.

Over the years, many deep neural networks (R-CNN, Faster R-CNN, SSD, Retina Net, YOLO, etc) have been developed to solve object detection tasks. They are quite good at the tasks.

Python deep learning libraries PyTorch and MXNet provide an implementation of these algorithms through helper modules 'torchtext’ and 'gluoncv’. We can simply load these neural networks with weights and make predictions by giving input images.

Text Classification

Text Classification


Text classification also referred to as document classification is a problem in computer science where each text document is assigned a unique category or label based on its content.

In order to classify text documents using deep neural networks, the text content of documents needs to be converted to real values. There are many approaches to converting text data to real-valued data like bag of words (word frequency, one-hot encoding, etc), Tf-IDF, Word embeddings, character embeddings, etc.

Once data is converted to real-valued data, deep neural networks of different types (Multi-Layer Perceptron, CNN, LSTM, etc) can be used to classify text documents. Neural networks can be designed with any Python deep learning library. Many libraries provide helper functionalities to handle text data.

Text Generation

Text Generation


Text generation also referred to as natural language generation is a sub-field of natural language processing (NLP) involving generation of new text. Text generation has various applications like generating reports, image captions, chatbots, etc.

Deep neural networks especially Recurrent neural networks and their variants (LSTM, GRU, etc) are proven to give good results for text generation tasks due to their ability to remember sequences.

Python deep learning libraries PyTorch, keras, MXNet, Flax, etc can be used to design RNNs to solve text generation task.

Interpret Predictions Of Deep Neural Networks

Interpret Predictions Of Deep Neural Networks


After training deep neural networks, we generally evaluate the performance of model by calculating and visualizing various ML Metrics (confusion matrix, ROC AUC curve, precision-recall curve, silhouette Analysis, elbow method, etc).

These metrics are normally a good starting point. But in many situations, they don’t give a 100% picture of model performance. E.g., A simple cat vs dog image classifier can be using background pixels to classify images instead of actual object (cat or dog) pixels.

In these situations, our ML metrics will give good results. But we should always be a little skeptical of model performance.

We can dive further deep and try to understand how our model is performing on an individual example by interpreting results. Various algorithms have been developed over time to interpret predictions of deep neural networks and many Python libraries (lime, eli5, treeinterpreter, shap, captum, etc) provide their implementation.

Learning Rate Schedulers

Learning Rate Schedulers


Learning rate is one of the most important hyperparameters during training of deep neural networks. A good learning rate can help neural networks converge quite faster.

Various experiments have shown that varying learning rate during training gives quite better results compared to keeping it constant throughout training process. It is recommended to gradually reduce learning rate over time during training. The process of changing learning rate during training is referred to as learning rate scheduling or learning rate annealing. The learning rate can be changed after each epoch or each batch.

Python deep learning libraries provide various ways to perform learning rate scheduling. Some common LR scheduling techniques like step LR, exponential LR, lambda LR, cyclic LR, cosine LR, etc are available in majority of libraries.