Foundations of Artificial Intelligence (AI for Beginners)

Topics covered

• •Understand what AI is and how weak AI differs from strong AI (AGI).
• •Learn about the Turing test and the problem of defining intelligence.
• •Master the top-down (symbolic) and bottom-up (neural network) approaches.

Topics covered

• •Understand how a perceptron is structured and how it's trained via gradient descent.
• •Build a multilayer network "from scratch": layers, activation functions, losses, backpropagation.
• •Learn the basics of working with PyTorch and TensorFlow/Keras.

Topics covered

• •Learn the basics of image processing with OpenCV.
• •Understand the principle of convolution, pooling, and CNN architecture; know the classic architectures.
• •Apply pretrained networks and transfer learning.

Topics covered

• •Understand autoencoders and variational autoencoders (VAEs) and their applications.
• •Learn how GANs work: generator, discriminator, adversarial training.
• •Master object detection (IoU/mAP metrics, the R-CNN family, YOLO/SSD).

Topics covered

• •Master classic text representations: Bag-of-Words, TF-IDF, n-grams.
• •Understand semantic embeddings (Word2Vec, GloVe) and their properties.
• •Learn about language modeling and training your own embeddings (CBoW/Skip-gram).

Topics covered

• •Understand the attention mechanism and its role in seq2seq tasks.
• •Learn the transformer architecture: self-attention, multi-head attention, positional encoding.
• •Understand BERT, pretraining, and fine-tuning; solve the NER task.

Topics covered

• •Understand the principle of genetic algorithms and the class of problems they're useful for.
• •Learn the basics of reinforcement learning: environment, reward, policy; the Policy Gradient and Actor-Critic algorithms.
• •Understand the multi-agent approach and emergent behavior.