diff --git a/Cargo.toml b/Cargo.toml
index fc0530c0..a8a12f3a 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -14,7 +14,7 @@ keywords = ["deep-learning", "neural-networks", "machine-learning", "framework"]
 license = "MIT OR Apache-2.0"
 
 [dependencies]
-collenchyma = { version = "0.0.8", default-features = false, features = ["native"] } # native feature to read/write data into tensors
+collenchyma = { version = "0.0.9", default-features = false, features = ["native"] } # native feature to read/write data into tensors
 collenchyma-blas = { version = "0.2.0", default-features = false, features = ["native"] } # only compiles with native feature
 collenchyma-nn = { version = "0.3.2", default-features = false }
 
diff --git a/benches/network_benches.rs b/benches/network_benches.rs
index e27253d7..50fc39e3 100644
--- a/benches/network_benches.rs
+++ b/benches/network_benches.rs
@@ -72,8 +72,8 @@ mod cuda {
     fn bench_mnsit_forward_1(b: &mut Bencher) {
         let mut cfg = SequentialConfig::default();
         // set up input
-        cfg.add_input("in", &vec![1, 30, 30]);
-        cfg.add_input("label", &vec![1, 1, 10]);
+        cfg.add_input("in", &[1, 30, 30]);
+        cfg.add_input("label", &[1, 1, 10]);
         // set up sigmoid
         let mut sig_cfg = LayerConfig::new("sig", LayerType::Sigmoid);
         sig_cfg.add_input("in");
@@ -96,7 +96,7 @@ mod cuda {
             backend.clone(), &LayerConfig::new("network", LayerType::Sequential(cfg)));
 
         let _ = timeit_loops!(10, {
-            let inp = SharedTensor::<f32>::new(backend.device(), &vec![1, 30, 30]).unwrap();
+            let inp = SharedTensor::<f32>::new(backend.device(), &[1, 30, 30]).unwrap();
             let inp_lock = Arc::new(RwLock::new(inp));
 
             network.forward(&[inp_lock]);
@@ -120,7 +120,7 @@ mod cuda {
     fn alexnet_forward(b: &mut Bencher) {
         let mut cfg = SequentialConfig::default();
         // Layer: data
-        cfg.add_input("data", &vec![128, 3, 224, 224]);
+        cfg.add_input("data", &[128, 3, 224, 224]);
         // Layer: conv1
         let conv1_layer_cfg = ConvolutionConfig {
             num_output: 64,
@@ -260,7 +260,7 @@ mod cuda {
 
         let func = || {
             let forward_time = timeit_loops!(1, {
-                let inp = SharedTensor::<f32>::new(backend.device(), &vec![128, 3, 112, 112]).unwrap();
+                let inp = SharedTensor::<f32>::new(backend.device(), &[128, 3, 112, 112]).unwrap();
 
                 let inp_lock = Arc::new(RwLock::new(inp));
                 network.forward(&[inp_lock]);
@@ -277,7 +277,7 @@ mod cuda {
         // let _ = env_logger::init();
         let mut cfg = SequentialConfig::default();
         // Layer: data
-        cfg.add_input("data", &vec![128, 3, 112, 112]);
+        cfg.add_input("data", &[128, 3, 112, 112]);
         // Layer: conv1
         let conv1_layer_cfg = ConvolutionConfig {
             num_output: 32,
@@ -416,7 +416,7 @@ mod cuda {
             backend.clone(), &LayerConfig::new("network", LayerType::Sequential(cfg)));
 
         let mut func = || {
-            let inp = SharedTensor::<f32>::new(backend.device(), &vec![128, 3, 112, 112]).unwrap();
+            let inp = SharedTensor::<f32>::new(backend.device(), &[128, 3, 112, 112]).unwrap();
 
             let inp_lock = Arc::new(RwLock::new(inp));
             network.forward(&[inp_lock]);
diff --git a/examples/benchmarks.rs b/examples/benchmarks.rs
index 5075a63f..d8eb076b 100644
--- a/examples/benchmarks.rs
+++ b/examples/benchmarks.rs
@@ -120,7 +120,7 @@ fn bench_alexnet() {
 #[cfg(all(feature="cuda", not(feature="native")))]
 fn bench_alexnet() {
     let mut cfg = SequentialConfig::default();
-    cfg.add_input("data", &vec![128, 3, 224, 224]);
+    cfg.add_input("data", &[128, 3, 224, 224]);
 
     let conv1_layer_cfg = ConvolutionConfig { num_output: 64, filter_shape: vec![11], padding: vec![2], stride: vec![4] };
     cfg.add_layer(LayerConfig::new("conv1", conv1_layer_cfg));
@@ -160,7 +160,7 @@ fn bench_alexnet() {
         let func = || {
             let forward_time = timeit_loops!(1, {
                 {
-                    let inp = SharedTensor::<f32>::new(backend.device(), &vec![128, 3, 224, 224]).unwrap();
+                    let inp = SharedTensor::<f32>::new(backend.device(), &[128, 3, 224, 224]).unwrap();
 
                     let inp_lock = Arc::new(RwLock::new(inp));
                     network.forward(&[inp_lock.clone()]);
@@ -202,7 +202,7 @@ fn bench_overfeat() {
 #[cfg(all(feature="cuda", not(feature="native")))]
 fn bench_overfeat() {
     let mut cfg = SequentialConfig::default();
-    cfg.add_input("data", &vec![128, 3, 231, 231]);
+    cfg.add_input("data", &[128, 3, 231, 231]);
 
     let conv1_layer_cfg = ConvolutionConfig { num_output: 96, filter_shape: vec![11], padding: vec![0], stride: vec![4] };
     cfg.add_layer(LayerConfig::new("conv1", conv1_layer_cfg));
@@ -242,7 +242,7 @@ fn bench_overfeat() {
         let func = || {
             let forward_time = timeit_loops!(1, {
                 {
-                    let inp = SharedTensor::<f32>::new(backend.device(), &vec![128, 3, 231, 231]).unwrap();
+                    let inp = SharedTensor::<f32>::new(backend.device(), &[128, 3, 231, 231]).unwrap();
 
                     let inp_lock = Arc::new(RwLock::new(inp));
                     network.forward(&[inp_lock.clone()]);
@@ -284,7 +284,7 @@ fn bench_vgg_a() {
 #[cfg(all(feature="cuda", not(feature="native")))]
 fn bench_vgg_a() {
     let mut cfg = SequentialConfig::default();
-    cfg.add_input("data", &vec![64, 3, 224, 224]);
+    cfg.add_input("data", &[64, 3, 224, 224]);
 
     let conv1_layer_cfg = ConvolutionConfig { num_output: 64, filter_shape: vec![3], padding: vec![1], stride: vec![1] };
     cfg.add_layer(LayerConfig::new("conv1", conv1_layer_cfg));
@@ -339,7 +339,7 @@ fn bench_vgg_a() {
         let func = || {
             let forward_time = timeit_loops!(1, {
                 {
-                    let inp = SharedTensor::<f32>::new(backend.device(), &vec![64, 3, 224, 224]).unwrap();
+                    let inp = SharedTensor::<f32>::new(backend.device(), &[64, 3, 224, 224]).unwrap();
 
                     let inp_lock = Arc::new(RwLock::new(inp));
                     network.forward(&[inp_lock.clone()]);
diff --git a/src/layer.rs b/src/layer.rs
index feee31b3..38a2bacd 100644
--- a/src/layer.rs
+++ b/src/layer.rs
@@ -203,8 +203,8 @@ impl<B: IBackend> Layer<B> {
             }
 
             let backend: Rc<IBackend<F=B::F>> = self.backend.clone();
-            blob_data = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &vec![1,1,1]).unwrap())); // [1,1,1] for CUDA
-            blob_gradient = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &vec![1,1,1]).unwrap())); // [1,1,1] for CUDA
+            blob_data = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &[1,1,1]).unwrap())); // [1,1,1] for CUDA
+            blob_gradient = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &[1,1,1]).unwrap())); // [1,1,1] for CUDA
         }
         self.output_blob_names.push(blob_name.clone());
         self.output_blobs_data.push(blob_data.clone());
@@ -227,8 +227,8 @@ impl<B: IBackend> Layer<B> {
         info!("{} -> {}", self.name, blob_name);
 
         let backend: Rc<IBackend<F=B::F>> = self.backend.clone();
-        let output_data = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &vec![1,1,1]).unwrap())); // [1,1,1] for CUDA
-        let output_gradient = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &vec![1,1,1]).unwrap())); // [1,1,1] for CUDA
+        let output_data = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &[1,1,1]).unwrap())); // [1,1,1] for CUDA
+        let output_gradient = Arc::new(RwLock::new(SharedTensor::new(backend.device(), &[1,1,1]).unwrap())); // [1,1,1] for CUDA
         self.output_blobs_data.push(output_data);
         self.output_blobs_gradient.push(output_gradient);
     }
@@ -460,7 +460,7 @@ impl<B: IBackend> Layer<B> {
 
         let forward_time = timeit_loops!(1, {
             if self.is_using_in_place() {
-                self.worker.forward(&self.backend, &vec![], &self.weights_data, &mut self.output_blobs_data);
+                self.worker.forward(&self.backend, &[], &self.weights_data, &mut self.output_blobs_data);
             } else {
                 self.worker.forward(&self.backend, &self.input_blobs_data, &self.weights_data, &mut self.output_blobs_data);
             }
@@ -498,8 +498,8 @@ impl<B: IBackend> Layer<B> {
         if self.is_using_in_place() {
             self.worker.backward_input(&self.backend,
                                  &self.weights_data,
-                                 &vec![],
-                                 &vec![],
+                                 &[],
+                                 &[],
                                  &self.input_blobs_data,
                                  &mut self.input_blobs_gradient)
         } else {
diff --git a/src/layers/common/convolution.rs b/src/layers/common/convolution.rs
index d7caac0e..e6c18583 100644
--- a/src/layers/common/convolution.rs
+++ b/src/layers/common/convolution.rs
@@ -252,12 +252,12 @@ mod tests {
             stride: vec![4],
         };
         let layer = Convolution::<Backend<Cuda>>::from_config(&cfg);
-        let num_spatial_dims = layer.num_spatial_dims(&vec![1, 3, 224, 224]);
+        let num_spatial_dims = layer.num_spatial_dims(&[1, 3, 224, 224]);
         assert_eq!(2, num_spatial_dims);
         assert_eq!(vec![11, 11], layer.spatial_filter_dims(2));
         assert_eq!(vec![2, 2], layer.padding_dims(2));
         assert_eq!(vec![4, 4], layer.stride_dims(2));
-        assert_eq!(vec![64, 3, 11, 11], layer.calculate_filter_shape(&vec![1, 3, 224, 224]));
-        assert_eq!(vec![1, 64, 55, 55], layer.calculate_output_shape(&vec![1, 3, 224, 224]));
+        assert_eq!(vec![64, 3, 11, 11], layer.calculate_filter_shape(&[1, 3, 224, 224]));
+        assert_eq!(vec![1, 64, 55, 55], layer.calculate_output_shape(&[1, 3, 224, 224]));
     }
 }
diff --git a/src/layers/common/sequential.rs b/src/layers/common/sequential.rs
index b10d4120..782c5f8a 100644
--- a/src/layers/common/sequential.rs
+++ b/src/layers/common/sequential.rs
@@ -43,7 +43,7 @@ impl<B: IBackend + LayerOps<f32> + 'static> Sequential<B> {
     pub fn from_config(backend: Rc<B>, config: &SequentialConfig) -> Sequential<B> {
         let mut layer = Self::empty();
 
-        layer.init_layers(backend, &config.clone());
+        layer.init_layers(backend, config);
 
         layer
     }
diff --git a/src/util.rs b/src/util.rs
index b87f8225..1dca48e0 100644
--- a/src/util.rs
+++ b/src/util.rs
@@ -59,7 +59,7 @@ pub fn write_batch_sample<T: NumCast + ::std::marker::Copy>(tensor: &mut SharedT
 /// Create a Collenchyma SharedTensor for a scalar value.
 pub fn native_scalar<T: NumCast + ::std::marker::Copy>(scalar: T) -> SharedTensor<T> {
     let native = native_backend();
-    let mut shared_scalar = SharedTensor::<T>::new(native.device(), &vec![1]).unwrap();
+    let mut shared_scalar = SharedTensor::<T>::new(native.device(), &1).unwrap();
     write_to_memory(shared_scalar.get_mut(native.device()).unwrap(), &[scalar]);
 
     shared_scalar
diff --git a/tests/layer_specs.rs b/tests/layer_specs.rs
index dba2be6f..0aa28f5e 100644
--- a/tests/layer_specs.rs
+++ b/tests/layer_specs.rs
@@ -60,7 +60,7 @@ mod layer_spec {
         #[test]
         fn can_create_single_layer_sequential_layer() {
             let mut model = SequentialConfig::default();
-            model.add_input("data", &vec![28, 28]);
+            model.add_input("data", &[28, 28]);
             model.add_layer(LayerConfig::new("sigmoid", LayerType::Sigmoid));
 
             Layer::from_config(cuda_backend(), &LayerConfig::new("model", LayerType::Sequential(model)));
@@ -69,7 +69,7 @@ mod layer_spec {
         #[test]
         fn can_create_simple_network_sequential_layer() {
             let mut model = SequentialConfig::default();
-            model.add_input("data", &vec![1, 784]);
+            model.add_input("data", &[1, 784]);
             model.add_layer(LayerConfig::new("linear1", LinearConfig { output_size: 1568 }));
             model.add_layer(LayerConfig::new("sigmoid", LayerType::Sigmoid));
             model.add_layer(LayerConfig::new("linear2", LinearConfig { output_size: 10 }));
@@ -83,12 +83,12 @@ mod layer_spec {
             let cuda_backend = cuda_backend();
 
             let mut normal_model = SequentialConfig::default();
-            normal_model.add_input("data", &vec![3]);
+            normal_model.add_input("data", &[3]);
             normal_model.add_layer(LayerConfig::new("sigmoid", LayerType::Sigmoid));
             let mut normal_network = Layer::from_config(cuda_backend.clone(), &LayerConfig::new("normal_model", LayerType::Sequential(normal_model)));
 
             let mut reshape_model = SequentialConfig::default();
-            reshape_model.add_input("data", &vec![3]);
+            reshape_model.add_input("data", &[3]);
             reshape_model.add_layer(LayerConfig::new("reshape", ReshapeConfig { shape: vec![1, 1, 3] }));
             reshape_model.add_layer(LayerConfig::new("sigmoid", LayerType::Sigmoid));
             let mut reshape_network = Layer::from_config(cuda_backend.clone(), &LayerConfig::new("reshape_model", LayerType::Sequential(reshape_model)));