Hfrxdjt

Does detail obscure or enhance action?

Doing something right before you need it - expression for this?

Why is 150k or 200k jobs considered good when there's 300k+ births a month?

Fully-Firstable Anagram Sets

Could an aircraft fly or hover using only jets of compressed air?

How much RAM could one put in a typical 80386 setup?

Is it possible to run Internet Explorer on OS X El Capitan?

Which country benefited the most from UN Security Council vetoes?

Can a vampire attack twice with their claws using Multiattack?

How do I deal with an unproductive colleague in a small company?

Is it inappropriate for a student to attend their mentor's dissertation defense?

Approximately how much travel time was saved by the opening of the Suez Canal in 1869?

Is it possible to do 50 km distance without any previous training?

Does an object always see its latest internal state irrespective of thread?

Intersection point of 2 lines defined by 2 points each

Codimension of non-flat locus

Is it tax fraud for an individual to declare non-taxable revenue as taxable income? (US tax laws)

dbcc cleantable batch size explanation

Are the number of citations and number of published articles the most important criteria for a tenure promotion?

Do infinite dimensional systems make sense?

What is a clear way to write a bar that has an extra beat?

How to format long polynomial?

What's the output of a record needle playing an out-of-speed record

Accidentally leaked the solution to an assignment, what to do now? (I'm the prof)

Binary classification of a sequance of vectors using Keras

0

$begingroup$

I have a list of vectors (shape of one vector = (1, 1000)), and I want to use something like LSTM to predict if a sequence is legal or not.
I'm trying to following architecture:

number_of_vectors = 2
x_in = Input(shape=(1, number_of_vectors * 1000))
x = LSTM(100, dropout=0.2, recurrent_dropout=0.2)(x_in)
x = Dense(1, activation='sigmoid')(x)
model = Model(input=x_in, output=x)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Each data sample is a list containing 2 ndarrays (of the vectors), and a binary value (legal/illegal).

What are the steps needed to pre-process the data, and correct the model's architecture, in order to make this work ?

classification keras lstm binary vector-space-models

share|improve this question

asked 6 hours ago

Miko DikoMiko Diko

1062

$endgroup$

add a comment | 

0

$begingroup$

I have a list of vectors (shape of one vector = (1, 1000)), and I want to use something like LSTM to predict if a sequence is legal or not.
I'm trying to following architecture:

number_of_vectors = 2
x_in = Input(shape=(1, number_of_vectors * 1000))
x = LSTM(100, dropout=0.2, recurrent_dropout=0.2)(x_in)
x = Dense(1, activation='sigmoid')(x)
model = Model(input=x_in, output=x)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Each data sample is a list containing 2 ndarrays (of the vectors), and a binary value (legal/illegal).

What are the steps needed to pre-process the data, and correct the model's architecture, in order to make this work ?

classification keras lstm binary vector-space-models

share|improve this question

asked 6 hours ago

Miko DikoMiko Diko

1062

$endgroup$

add a comment | 

$begingroup$

I have a list of vectors (shape of one vector = (1, 1000)), and I want to use something like LSTM to predict if a sequence is legal or not.
I'm trying to following architecture:

number_of_vectors = 2
x_in = Input(shape=(1, number_of_vectors * 1000))
x = LSTM(100, dropout=0.2, recurrent_dropout=0.2)(x_in)
x = Dense(1, activation='sigmoid')(x)
model = Model(input=x_in, output=x)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Each data sample is a list containing 2 ndarrays (of the vectors), and a binary value (legal/illegal).

What are the steps needed to pre-process the data, and correct the model's architecture, in order to make this work ?

classification keras lstm binary vector-space-models

share|improve this question

asked 6 hours ago

Miko DikoMiko Diko

1062

$endgroup$

number_of_vectors = 2
x_in = Input(shape=(1, number_of_vectors * 1000))
x = LSTM(100, dropout=0.2, recurrent_dropout=0.2)(x_in)
x = Dense(1, activation='sigmoid')(x)
model = Model(input=x_in, output=x)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

share|improve this question

asked 6 hours ago

Miko DikoMiko Diko

1062

share|improve this question

asked 6 hours ago

Miko DikoMiko Diko

1062

asked 6 hours ago

Miko DikoMiko Diko

1062

asked 6 hours ago

Miko DikoMiko Diko

1062