What concerns do you have about this course?    (Please respond in complete sentences.)

If you need help with a paper, where do you go? Who do you ask for help?   (Please respond in complete sentences.)

Ref: coinmarketcap.com Bitcoin is _________________________________________________. It eliminated the key problem with digital currencies in the past (you can make a perfect digital copy and “double spend”) Every transaction would be kept in an immutable ledger and the ledger would be distributed across many different computers.

Gradient vanishing means the gradient of neural networks during training is too small or too large (unstable) ; therefore, neural networks cannot learn more effectively. Which one is not a method or model to mitigate the gradient vanishing problem in neural networks? 

Private key is just a random number. The public key is mathematically linked to the private key. If currency is transferred, the sender uses a digital signature algorithm to sign the token over to someone else’s address.    It is easy to go from the private key to the public key – but very difficult to go from public to private. A message needs to go from Sender to Receiver Receiver gives the Sender a lock Sender locks the message (ciphertext) and transmits to Receiver Only the Receiver can decrypt because they have the key The lock is (1)_______________ The key to open the lock is (2)__________ (3) ___________ mathematically reveals that the sender has the private key associated with the senders public address. 

The above image data set contains an image from zero to nine, and a deep neural network classifies its label condition based on pixel information. In this case, it is an example of (1)__________ in the field of (2)____________   

Ref: coinmarketcap Ethereum began in 2015 with Vitalik Buterin Ethereum  allows for running of computer programs. So Ethereum is a distributed computational platform offering functionality via offering a ______________

___________________: using a pre-trained language model with a large corpus and does additional training with your dataset for specific task. It requires low resources but generally shows good performance as follows:      

What is not a hyperparameter for deep neural network (DNN)?

Dean Burns favorite drink is what? The answer is milk.