MindLink

Relier Colonnes

Parties jouées 1

Créer une copie

À propos de cette activité

Connect concepts, master Machine Learning.

MindLink: Create Matching Pairs is an interactive challenge for 1st year AIML students. Participants will match key terms with their correct definitions, covering Machine Learning, Deep Learning, and Reinforcement Learning concepts across multiple rounds.

A fun and engaging way to strengthen your ML knowledge, sharpen recall, and test conceptual understanding.

Créé par

LEELANANDHA KISHORE K S BTech_AIML

India

Téléchargez la version pour jouer sur papier

Top 10 résultats

Il n'y a toujours pas de résultats pour ce jeu. Soyez le premier à apparaître dans le classement! Connectez-vous pour vous identifier.

Créez votre propre jeu gratuite à partir de notre créateur de jeu

Affrontez vos amis pour voir qui obtient le meilleur score dans ce jeu

Créer un défi

		%
	Anonyme	%
		%
		%

Imprimez votre jeu

MindLink


Relier Pairs MindLinkVersion en ligne Connect concepts, master Machine Learning. MindLink: Create Matching Pairs is an interactive challenge for 1st year AIML students. Participants will match key terms with their correct definitions, covering Machine Learning, Deep Learning, and Reinforcement Learning concepts across multiple rounds. A fun and engaging way to strengthen your ML knowledge, sharpen recall, and test conceptual understanding. par LEELANANDHA KISHORE K S BTech_AIML 1 Supervised Learning 2 Training Data 3 Unsupervised Learning 4 Classification 5 Feature 6 Clustering 7 Regression 8 Label Learning with labeled data Output variable in supervised learning Predicting categories Predicting continuous values Data used to train the model Grouping similar data points Input variable in a model Learning with unlabeled data 1 Cross-Validation 2 Precision 3 Overfitting 4 Underfitting 5 Accuracy 6 Confusion Matrix 7 F1-Score 8 Recall Technique to assess model performance True positives / Predicted positives Model fails to capture patterns Correct predictions / Total predictions Harmonic mean of precision and recall Table showing true vs predicted labels Model fits training data too closely True positives / Actual positives 1 PCA 2 Standardization 3 Feature Selection 4 One-Hot Encoding 5 Tokenization 6 Dimensionality Reduction 7 Stop Words 8 Normalization Scaling features to a specific range Choosing important variables Breaking text into words or tokens Reduce number of features Common words removed during text processing Scaling to zero mean & unit variance Convert categorical to binary vectors Principal Component Analysis 1 Batch 2 Activation Function 3 Epoch 4 Perceptron 5 Neural Network 6 Perceptron 7 Gradient Descent 8 Dropout Adds non-linearity to network Algorithm to update weights Simplest type of neural network Optimization algorithm Regularization technique to prevent overfitting Model inspired by human brain Subset of data processed at a time One complete pass over training data 1 Time Series 2 RNN 3 CNN 4 GRU 5 LSTM 6 Convolution 7 Convolution 8 Sequence Data Data with order dependencies Convolutional Neural Network Recurrent Neural Network Gated Recurrent Unit Long Short-Term Memory network Feature extraction operation Sequential data over time Reducing spatial dimensions 1 Transformer 2 Self-Attention 3 BERT 4 Decoder 5 Encoder 6 Attention 7 NLP 8 Embedding Converts input to representation Attention within same sequence Focus on important parts of input Representation of data in vector space Pretrained transformer model Uses attention mechanism Generates output from representation Natural Language Processing 1 Policy 2 Episode 3 Reward 4 Action 5 Exploration 6 Environment 7 Agent 8 State Sequence of states, actions, rewards Learner or decision-maker World in which agent interacts Strategy to select actions Move taken by agent Trying new actions Feedback signal Current situation of agent 1 Discount Factor 2 Q-Learning 3 Policy Gradient 4 Exploitation 5 Bellman Equation 6 Value Function 7 Markov Decision Process 8 SARSA Future reward weighting On-policy RL algorithm Value-based RL algorithm Estimates expected reward Framework for RL problems Optimizes policy directly Computes value functions Using known best actions 1 Batch Normalization 2 Cross-Entropy 3 Regularization 4 Learning Rate 5 Softmax 6 Weight Initialization 7 Convergence 8 Hyperparameter Step size in gradient descent Loss function for classification When training stabilizes Parameter set before training Reduces overfitting Converts logits to probabilities Starting weights in neural nets Normalizes layer inputs 1 Overfitting 2 Transfer Learning 3 Feature Engineering 4 Reinforcement Learning 5 Fine-Tuning 6 Attention Mechanism 7 NLP 8 Deep Learning Creating new features Learning via rewards Model memorizes training data Using pretrained models Neural network-based learning Adjusting pretrained model on new data Focus on important input parts Processing human language

MindLink

Relier Colonnes

À propos de cette activité

Créé par

Téléchargez la version pour jouer sur papier

Top Jeux

Relier Colonnes

Cranial Nerves

Relier Colonnes

Cell Cycle Memory

Relier Colonnes

Balance Sheet & P & L

Relier Colonnes

appendicular skeleton

Relier Colonnes

The Bill of Rights

Relier Pairs

MindLinkVersion en ligne

par LEELANANDHA KISHORE K S BTech_AIML

Supervised Learning

Training Data

Unsupervised Learning

Classification

Feature

Clustering

Regression

Label

Cross-Validation

Precision

Overfitting

Underfitting

Accuracy

Confusion Matrix

F1-Score

Recall

PCA

Standardization

Feature Selection

One-Hot Encoding

Tokenization

Dimensionality Reduction

Stop Words

Normalization

Batch

Activation Function

Epoch

Perceptron

Neural Network

Perceptron

Gradient Descent

Dropout

Time Series

RNN

CNN

GRU

LSTM

Convolution

Convolution

Sequence Data

Transformer

Self-Attention

BERT

Decoder

Encoder

Attention

NLP

Embedding

Policy

Episode

Reward

Action

Exploration

Environment

Agent

State

Discount Factor

Q-Learning

Policy Gradient

Exploitation

Bellman Equation