المجالات المعرفية

الأسئلة التي يجيب عنها هذا المجال

• Why can data be written as a matrix?
• Which direction does the gradient actually point?
• Why can softmax be used as a probability?

الأسئلة التي يجيب عنها هذا المجال

• What separates “memorising” from “learning”?
• Why does a model that aces training fail in production?
• What can unlabelled data still be used for?

الأسئلة التي يجيب عنها هذا المجال

• What is a single neuron actually computing?
• How does backpropagation carry error backwards?
• Why are deeper networks harder to train?

الأسئلة التي يجيب عنها هذا المجال

• What exactly does a model see when it reads a word?
• Why does attention beat recurrence?
• Why does next-token prediction yield conversation?

الأسئلة التي يجيب عنها هذا المجال

• What does a convolution kernel actually learn?
• How do classification, detection and segmentation differ?
• How does a machine recover 3D from 2D images?

الأسئلة التي يجيب عنها هذا المجال

• Why does delayed reward make the problem hard?
• How do value functions and policy gradients divide the work?
• Why can RL improve large language models?

الأسئلة التي يجيب عنها هذا المجال

• What distribution is a generative model learning?
• Why is diffusion more stable than a GAN?
• How does a text prompt become an image?

الأسئلة التي يجيب عنها هذا المجال

• How are large models compressed onto consumer hardware?
• How do you evaluate when there is no answer key?
• Why is prompt injection so hard to eliminate?