You're right, optimizers were missed! In short, they guide deep learning models by adjusting parameters to minimize loss (think radio dial for best station). Key points: ➡️ Evaluate: Measure model performance with loss function. ➡️ Calculate: Determine how much to adjust each parameter. ➡️ Update: Adjust parameters based on calculations. ➡️ Repeat: Iterate until minimum loss is reached. Different optimizers exist, each with strengths and weaknesses (e.g., Gradient descent, Adam, RMSprop). Remember, this is just a starting point. Explore further to deepen your understanding!
Some were not well explained and some points like 10th and optimisers you have to spend more time on because these are the questions generally asked in the interview , thanks 👍
You missed to explain what is optimizers??
You're right, optimizers were missed! In short, they guide deep learning models by adjusting parameters to minimize loss (think radio dial for best station). Key points:
➡️ Evaluate: Measure model performance with loss function.
➡️ Calculate: Determine how much to adjust each parameter.
➡️ Update: Adjust parameters based on calculations.
➡️ Repeat: Iterate until minimum loss is reached.
Different optimizers exist, each with strengths and weaknesses (e.g., Gradient descent, Adam, RMSprop).
Remember, this is just a starting point. Explore further to deepen your understanding!
@@Analyticsvidhya please make a video of ml interview questions (technical question)
Some were not well explained and some points like 10th and optimisers you have to spend more time on because these are the questions generally asked in the interview , thanks 👍