Neural Networks Basics
This is the function used by most neurons to introduce non-linearity into the network.
What is an activation function?
This is the algorithm most commonly used to update weights during training.
What is gradient descent?
This type of neural network architecture is especially effective for analyzing image data.
What is a convolutional neural network?
This type of neural network is commonly used for sequences and time series.
What is a recurrent neural network?
This is the deep learning framework developed by Google.
What is TensorFlow?
This type of neural network connects every neuron in one layer to every neuron in the next.
What is a fully connected network?
This variant of gradient descent uses a subset of the data to compute updates.
What is mini-batch gradient descent
What categories existed in the CNN Competition dataset?
What is Dogs,Cats,Turtles,Penguins?
The RNN was made to mimic this human ability.
What is memory?
This pre-trained language model by OpenAI became the basis for ChatGPT.
What is GPT?
This common activation function outputs values between 0 and 1.
What is the sigmoid function?
This technique prevents overfitting by randomly disabling neurons during training.
What is dropout?
This famous automatic brand is known for using their Camera Only based CNN for Autonomous driving.
This RNN variant uses gates to better handle long-range dependencies.
What is an LSTM?
This AI system developed by DeepMind defeated world champion Lee Sedol in the game of Go using deep reinforcement learning.
What is AlphaGo?
This problem occurs when gradients become too small for effective learning, especially in deep networks.
What is the vanishing gradient problem?
This parameter controls how big a step the model takes during training updates.
What is the learning rate?
This operation reduces the spatial dimensions of the feature map.
What is pooling?
This RNN variant simplifies LSTMs by combining the forget and input gates into a single update gate.
What is a GRU (Gated Recurrent Unit)?
This chess-playing computer system defeated world champion Garry Kasparov in 1997, marking a historic moment in AI.
What is Deep Blue?
This function is used to compute the error between predicted outputs and actual labels for classification.
What is categorical cross-entropy?
This process involves dividing a dataset into two parts—one used to teach the model and the other to evaluate its performance.
What is a train-test split?
This layer in a CNN scans over an image using a kernel or filter.
What is a convolutional layer?
In a GRU, this gate determines how much of the previous memory to keep and how much new information to add.
What is the update gate?
This DeepMind system revolutionized biology by accurately predicting 3D protein structures from amino acid sequences.
What is AlphaFold?