mikkokotila

Keybase proof

I hereby claim:

• I am mikkokotila on github.
• I am mikkokotila (https://keybase.io/mikkokotila) on keybase.
• I have a public key whose fingerprint is 1415 6666 3A1C B257 ECA2 A86F 4308 1E9D C041 D0F8

To claim this, I am signing this object:

mikkokotila

    org  0x100        ; .com files always start 256 bytes into the segment

    ; int 21h is going to want...

    mov  dx, msg      ; the address of or message in dx
    mov  ah, 9        ; ah=9 - "print string" sub-function
    int  0x21         ; call dos services

    mov  dl, 0x0d     ; put CR into dl
    mov  ah, 2        ; ah=2 - "print character" sub-function

mikkokotila

# first we have to make sure to input data and params into the function
def breast_cancer_model(x_train, y_train, x_val, y_val, params):

    # next we can build the model exactly like we would normally do it
    model = Sequential()
    model.add(Dense(10, input_dim=x_train.shape[1],
                    activation=params['activation'],
                    kernel_initializer='normal'))
    
    model.add(Dropout(params['dropout']))

mikkokotila

# then we can go ahead and set the parameter space
p = {'lr': (0.5, 5, 10),
     'first_neuron':[4, 8, 16, 32, 64],
     'hidden_layers':[0, 1, 2],
     'batch_size': (2, 30, 10),
     'epochs': [150],
     'dropout': (0, 0.5, 5),
     'weight_regulizer':[None],
     'emb_output_dims': [None],
     'shape':['brick','long_funnel'],

mikkokotila

# and run the experiment
t = ta.Scan(x=x,
            y=y,
            model=breast_cancer_model,
            grid_downsample=0.01, 
            params=p,
            dataset_name='breast_cancer',
            experiment_no='1')

mikkokotila

p = {'lr': (0.8, 1.2, 3),
     'first_neuron':[4, 8, 16, 32, 64],
     'hidden_layers':[0, 1, 2],
     'batch_size': (1, 5, 5),
     'epochs': [50, 100, 150],
     'dropout': (0, 0.2, 3),
     'weight_regulizer':[None],
     'emb_output_dims': [None],
     'shape':['brick','long_funnel'],
     'kernel_initializer': ['uniform','normal'],

mikkokotila

def iris_model(x_train, y_train, x_val, y_val):

    model = Sequential()
    model.add(Dense(32, input_dim=8, activation='adam'))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(optimizer='relu', loss='binary_crossentropy')

    out = model.fit(x_train, y_train,
                    batch_size=24,
                    epochs=100,

mikkokotila

import talos
from keras.models import Sequential
from keras.layers import Dense

def minimal():

    x, y = talos.templates.datasets.iris()

    p = {'activation':['relu', 'elu'],
         'optimizer': ['Nadam', 'Adam'],

mikkokotila

import talos as ta
from keras.models import Sequential
from keras.layers import Dense

def minimal():

     x, y = ta.datasets.iris()

     p = {'activation':['relu', 'elu'],
          'optimizer': ['Nadam', 'Adam'],

mikkokotila

import signs as signs
import pandas as pd

# load some text
df = pd.read_csv('tweets.csv').text

# load vectors
e = signs.Embeds("glove.twitter.27B.25d.txt")

# get Keras embeddings layer