AI & Deep Learning Frameworks Flashcards

What is the purpose of a neural network in deep learning?

Answer: To model complex data relationships

The primary purpose of a neural network in deep learning is to model and learn complex patterns and relationships within data. Inspired by the human brain, these networks consist of interconnected layers of artificial neurons that process information, allowing them to perform tasks like classification, regression, and pattern recognition, often with high accuracy on large and intricate datasets.

Which activation function outputs values between 0 and 1?

Answer: Sigmoid

The Sigmoid activation function outputs values that are squashed into a range between 0 and 1. This characteristic makes it particularly useful in the output layer of binary classification problems, where the output can be interpreted as a probability. While once popular in hidden layers, its vanishing gradient problem has led to ReLU being preferred for those layers.

What is overfitting in deep learning?

Answer: Model learns noise and poorly generalizes

Overfitting in deep learning occurs when a model learns the training data too well, including its noise and specific idiosyncrasies, rather than the underlying general patterns. Consequently, while the model performs exceptionally on the training set, its performance significantly degrades when presented with new, unseen data, indicating poor generalization ability. This often happens when a model is too complex for the amount of training data available.

Which framework is developed by Google for machine learning?

Answer: TensorFlow

TensorFlow is an open-source machine learning framework developed by Google. It is widely used for building and training various types of neural networks and other machine learning models. TensorFlow provides a comprehensive ecosystem of tools, libraries, and community resources for research and production deployment across different platforms.

What is backpropagation used for?

Answer: Weight updates using gradients

Backpropagation is a fundamental algorithm used in training artificial neural networks to efficiently calculate the gradients of the loss function with respect to the network's weights. These gradients indicate the direction and magnitude by which the weights should be adjusted to minimize the loss. By iteratively updating the weights based on these gradients, backpropagation enables the network to learn from its errors and improve its performance.

Which layer type is commonly used in Convolutional Neural Networks (CNNs)?

Answer: Convolutional layer

The convolutional layer is a core component commonly used in Convolutional Neural Networks (CNNs), especially for tasks involving image and video processing. This layer applies a set of learnable filters (kernels) to the input data, performing a convolution operation to extract features such as edges, textures, or patterns. These extracted features are then passed to subsequent layers for further processing and analysis.

What is a common technique to prevent overfitting?

Answer: Dropout

Dropout is a powerful regularization technique used to prevent overfitting in neural networks. It works by randomly deactivating a percentage of neurons during each training step, forcing the network to learn more robust features and preventing over-reliance on any single neuron or specific connections. This effectively creates an ensemble of smaller networks, improving generalization.

Which library is popular for deep learning with Python?

Answer: PyTorch

PyTorch is an extremely popular open-source machine learning library widely adopted for deep learning research and development with Python. It provides a flexible framework for building and training neural networks, known for its dynamic computational graph and strong GPU acceleration capabilities. While other libraries like Scikit-learn, NumPy, and Pandas are essential for data science, PyTorch is specifically designed for deep learning.

What does the term 'epoch' mean in deep learning training?

Answer: One full training data pass

In deep learning training, an 'epoch' signifies one complete pass through the entire training dataset. During an epoch, the model processes every single training example, updates its internal parameters (weights and biases), and learns from the data. Multiple epochs are typically required for a model to converge and achieve good performance.